Delete checkpoint-456
Browse files- checkpoint-456/added_tokens.json +0 -5
- checkpoint-456/chat_template.jinja +0 -4
- checkpoint-456/config.json +0 -32
- checkpoint-456/generation_config.json +0 -9
- checkpoint-456/merges.txt +0 -0
- checkpoint-456/model-00001-of-00002.safetensors +0 -3
- checkpoint-456/model-00002-of-00002.safetensors +0 -3
- checkpoint-456/model.safetensors.index.json +0 -261
- checkpoint-456/optimizer.pt +0 -3
- checkpoint-456/rng_state.pth +0 -3
- checkpoint-456/scheduler.pt +0 -3
- checkpoint-456/special_tokens_map.json +0 -30
- checkpoint-456/tokenizer.json +0 -0
- checkpoint-456/tokenizer_config.json +0 -69
- checkpoint-456/trainer_state.json +0 -3226
- checkpoint-456/training_args.bin +0 -3
- checkpoint-456/vocab.json +0 -0
checkpoint-456/added_tokens.json
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"<|endofprompt|>": 100276,
|
3 |
-
"<|im_end|>": 100265,
|
4 |
-
"<|im_start|>": 100264
|
5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/chat_template.jinja
DELETED
@@ -1,4 +0,0 @@
|
|
1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
2 |
-
' + message['content'] + '<|im_end|>' + '
|
3 |
-
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
4 |
-
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
checkpoint-456/config.json
DELETED
@@ -1,32 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"architectures": [
|
3 |
-
"LlamaForCausalLM"
|
4 |
-
],
|
5 |
-
"attention_bias": false,
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id": 100257,
|
8 |
-
"embd_pdrop": 0.0,
|
9 |
-
"eos_token_id": 100265,
|
10 |
-
"head_dim": 128,
|
11 |
-
"hidden_act": "silu",
|
12 |
-
"hidden_size": 4096,
|
13 |
-
"initializer_range": 0.02,
|
14 |
-
"intermediate_size": 8192,
|
15 |
-
"max_position_embeddings": 262144,
|
16 |
-
"mlp_bias": false,
|
17 |
-
"model_type": "llama",
|
18 |
-
"num_attention_heads": 32,
|
19 |
-
"num_hidden_layers": 28,
|
20 |
-
"num_key_value_heads": 8,
|
21 |
-
"pad_token_id": 100257,
|
22 |
-
"pretraining_tp": 1,
|
23 |
-
"resid_pdrop": 0.0,
|
24 |
-
"rms_norm_eps": 1e-06,
|
25 |
-
"rope_scaling": null,
|
26 |
-
"rope_theta": 128000000,
|
27 |
-
"tie_word_embeddings": true,
|
28 |
-
"torch_dtype": "bfloat16",
|
29 |
-
"transformers_version": "4.52.4",
|
30 |
-
"use_cache": false,
|
31 |
-
"vocab_size": 102400
|
32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/generation_config.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 100257,
|
4 |
-
"do_sample": true,
|
5 |
-
"eos_token_id": 100265,
|
6 |
-
"pad_token_id": 100257,
|
7 |
-
"transformers_version": "4.52.4",
|
8 |
-
"use_cache": false
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-456/model-00001-of-00002.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:210c4bf7b2e60318aad8ecccb77e23cf8f0a04c42cf0793d4501fe8421fafa56
|
3 |
-
size 4983077832
|
|
|
|
|
|
|
|
checkpoint-456/model-00002-of-00002.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:20efe41d8e31211f8da04168416224856e59c48709229ab791c9d76253573477
|
3 |
-
size 3842234168
|
|
|
|
|
|
|
|
checkpoint-456/model.safetensors.index.json
DELETED
@@ -1,261 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"metadata": {
|
3 |
-
"total_size": 8825282560
|
4 |
-
},
|
5 |
-
"weight_map": {
|
6 |
-
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
7 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
8 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
9 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
12 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
15 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
17 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
18 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
21 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
24 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
-
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
26 |
-
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
-
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
30 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
-
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
35 |
-
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
36 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
-
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
39 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
42 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
-
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
44 |
-
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
45 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
-
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
48 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
-
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
53 |
-
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
-
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
58 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
-
"model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
62 |
-
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
63 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
-
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
65 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
66 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
-
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
71 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
72 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
73 |
-
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
74 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
75 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
76 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
77 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
78 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
79 |
-
"model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
80 |
-
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
81 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
82 |
-
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
83 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
84 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
85 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
86 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
87 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
88 |
-
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
89 |
-
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
90 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
91 |
-
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
92 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
93 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
94 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
95 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
96 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
97 |
-
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
98 |
-
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
99 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
100 |
-
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
101 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
102 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
103 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
104 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
105 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
106 |
-
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
107 |
-
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
108 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
109 |
-
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
110 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
111 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
112 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
113 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
114 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
115 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
116 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
117 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
119 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
120 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
121 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
122 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
-
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
125 |
-
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
126 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
127 |
-
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
128 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
129 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
130 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
131 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
132 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
133 |
-
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
134 |
-
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
135 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
136 |
-
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
138 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
139 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
140 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
141 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
142 |
-
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
143 |
-
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
144 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
145 |
-
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
146 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
147 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
148 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
149 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
150 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
151 |
-
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
152 |
-
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
153 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
154 |
-
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
155 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
156 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
157 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
158 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
159 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
160 |
-
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
161 |
-
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
162 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
163 |
-
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
164 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
165 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
166 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
167 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
168 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
169 |
-
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
170 |
-
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
171 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
172 |
-
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
173 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
174 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
175 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
176 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
177 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
178 |
-
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
179 |
-
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
180 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
181 |
-
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
182 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
183 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
184 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
185 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
186 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
187 |
-
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
188 |
-
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
189 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
190 |
-
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
191 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
192 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
193 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
194 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
195 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
196 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
197 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
198 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
200 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
201 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
202 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
203 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
204 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
205 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
206 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
208 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
209 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
210 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
211 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
212 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
213 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
214 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
215 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
216 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
218 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
219 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
220 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
221 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
222 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
223 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
224 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
225 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
226 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
227 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
228 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
229 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
230 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
231 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
232 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
233 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
234 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
235 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
236 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
237 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
238 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
239 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
240 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
241 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
242 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
243 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
244 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
245 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
246 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
247 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
248 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
249 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
250 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
251 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
252 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
253 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
254 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
255 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
256 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
257 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
258 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
259 |
-
"model.norm.weight": "model-00002-of-00002.safetensors"
|
260 |
-
}
|
261 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:76b5b1c73b4023cc940f91eec64ba0b9763028fa4f7a4d0ff669c6718ea39670
|
3 |
-
size 11466963134
|
|
|
|
|
|
|
|
checkpoint-456/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b0b8a6e3878f9402461193b241d8f1ee8546c6ad03f43e5b9dab8f4fc8c4d065
|
3 |
-
size 14244
|
|
|
|
|
|
|
|
checkpoint-456/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:3510516fc5ba13cb1d74463ede84d0e0262efc5d459b243129930e6ad58a29f1
|
3 |
-
size 1064
|
|
|
|
|
|
|
|
checkpoint-456/special_tokens_map.json
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|im_end|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<|endoftext|>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-456/tokenizer_config.json
DELETED
@@ -1,69 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"100257": {
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"100258": {
|
13 |
-
"content": "<|fim_prefix|>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"100259": {
|
21 |
-
"content": "<|fim_middle|>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"100260": {
|
29 |
-
"content": "<|fim_suffix|>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"100264": {
|
37 |
-
"content": "<|im_start|>",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": false
|
43 |
-
},
|
44 |
-
"100265": {
|
45 |
-
"content": "<|im_end|>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": true
|
51 |
-
},
|
52 |
-
"100276": {
|
53 |
-
"content": "<|endofprompt|>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": true
|
59 |
-
}
|
60 |
-
},
|
61 |
-
"bos_token": "<|endoftext|>",
|
62 |
-
"clean_up_tokenization_spaces": false,
|
63 |
-
"eos_token": "<|im_end|>",
|
64 |
-
"extra_special_tokens": {},
|
65 |
-
"model_max_length": 262144,
|
66 |
-
"pad_token": "<|endoftext|>",
|
67 |
-
"tokenizer_class": "GPT2Tokenizer",
|
68 |
-
"unk_token": "<|endoftext|>"
|
69 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/trainer_state.json
DELETED
@@ -1,3226 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_global_step": null,
|
3 |
-
"best_metric": null,
|
4 |
-
"best_model_checkpoint": null,
|
5 |
-
"epoch": 3.96943231441048,
|
6 |
-
"eval_steps": 500,
|
7 |
-
"global_step": 456,
|
8 |
-
"is_hyper_param_search": false,
|
9 |
-
"is_local_process_zero": true,
|
10 |
-
"is_world_process_zero": true,
|
11 |
-
"log_history": [
|
12 |
-
{
|
13 |
-
"epoch": 0.008733624454148471,
|
14 |
-
"grad_norm": 2.234375,
|
15 |
-
"learning_rate": 0.0,
|
16 |
-
"loss": 2.578,
|
17 |
-
"step": 1
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"epoch": 0.017467248908296942,
|
21 |
-
"grad_norm": 2.515625,
|
22 |
-
"learning_rate": 4.5454545454545457e-07,
|
23 |
-
"loss": 2.6324,
|
24 |
-
"step": 2
|
25 |
-
},
|
26 |
-
{
|
27 |
-
"epoch": 0.026200873362445413,
|
28 |
-
"grad_norm": 2.546875,
|
29 |
-
"learning_rate": 9.090909090909091e-07,
|
30 |
-
"loss": 2.6563,
|
31 |
-
"step": 3
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"epoch": 0.034934497816593885,
|
35 |
-
"grad_norm": 2.21875,
|
36 |
-
"learning_rate": 1.3636363636363636e-06,
|
37 |
-
"loss": 2.5986,
|
38 |
-
"step": 4
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.043668122270742356,
|
42 |
-
"grad_norm": 2.40625,
|
43 |
-
"learning_rate": 1.8181818181818183e-06,
|
44 |
-
"loss": 2.6456,
|
45 |
-
"step": 5
|
46 |
-
},
|
47 |
-
{
|
48 |
-
"epoch": 0.05240174672489083,
|
49 |
-
"grad_norm": 2.28125,
|
50 |
-
"learning_rate": 2.2727272727272728e-06,
|
51 |
-
"loss": 2.638,
|
52 |
-
"step": 6
|
53 |
-
},
|
54 |
-
{
|
55 |
-
"epoch": 0.0611353711790393,
|
56 |
-
"grad_norm": 2.421875,
|
57 |
-
"learning_rate": 2.7272727272727272e-06,
|
58 |
-
"loss": 2.6678,
|
59 |
-
"step": 7
|
60 |
-
},
|
61 |
-
{
|
62 |
-
"epoch": 0.06986899563318777,
|
63 |
-
"grad_norm": 2.328125,
|
64 |
-
"learning_rate": 3.181818181818182e-06,
|
65 |
-
"loss": 2.6304,
|
66 |
-
"step": 8
|
67 |
-
},
|
68 |
-
{
|
69 |
-
"epoch": 0.07860262008733625,
|
70 |
-
"grad_norm": 2.046875,
|
71 |
-
"learning_rate": 3.6363636363636366e-06,
|
72 |
-
"loss": 2.6253,
|
73 |
-
"step": 9
|
74 |
-
},
|
75 |
-
{
|
76 |
-
"epoch": 0.08733624454148471,
|
77 |
-
"grad_norm": 2.109375,
|
78 |
-
"learning_rate": 4.0909090909090915e-06,
|
79 |
-
"loss": 2.6161,
|
80 |
-
"step": 10
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.09606986899563319,
|
84 |
-
"grad_norm": 2.015625,
|
85 |
-
"learning_rate": 4.5454545454545455e-06,
|
86 |
-
"loss": 2.6971,
|
87 |
-
"step": 11
|
88 |
-
},
|
89 |
-
{
|
90 |
-
"epoch": 0.10480349344978165,
|
91 |
-
"grad_norm": 1.75,
|
92 |
-
"learning_rate": 5e-06,
|
93 |
-
"loss": 2.5767,
|
94 |
-
"step": 12
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"epoch": 0.11353711790393013,
|
98 |
-
"grad_norm": 1.703125,
|
99 |
-
"learning_rate": 5.4545454545454545e-06,
|
100 |
-
"loss": 2.5748,
|
101 |
-
"step": 13
|
102 |
-
},
|
103 |
-
{
|
104 |
-
"epoch": 0.1222707423580786,
|
105 |
-
"grad_norm": 1.6328125,
|
106 |
-
"learning_rate": 5.90909090909091e-06,
|
107 |
-
"loss": 2.5845,
|
108 |
-
"step": 14
|
109 |
-
},
|
110 |
-
{
|
111 |
-
"epoch": 0.13100436681222707,
|
112 |
-
"grad_norm": 1.5234375,
|
113 |
-
"learning_rate": 6.363636363636364e-06,
|
114 |
-
"loss": 2.6236,
|
115 |
-
"step": 15
|
116 |
-
},
|
117 |
-
{
|
118 |
-
"epoch": 0.13973799126637554,
|
119 |
-
"grad_norm": 1.3359375,
|
120 |
-
"learning_rate": 6.818181818181818e-06,
|
121 |
-
"loss": 2.6045,
|
122 |
-
"step": 16
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 0.14847161572052403,
|
126 |
-
"grad_norm": 1.296875,
|
127 |
-
"learning_rate": 7.272727272727273e-06,
|
128 |
-
"loss": 2.617,
|
129 |
-
"step": 17
|
130 |
-
},
|
131 |
-
{
|
132 |
-
"epoch": 0.1572052401746725,
|
133 |
-
"grad_norm": 1.15625,
|
134 |
-
"learning_rate": 7.727272727272727e-06,
|
135 |
-
"loss": 2.5447,
|
136 |
-
"step": 18
|
137 |
-
},
|
138 |
-
{
|
139 |
-
"epoch": 0.16593886462882096,
|
140 |
-
"grad_norm": 1.1796875,
|
141 |
-
"learning_rate": 8.181818181818183e-06,
|
142 |
-
"loss": 2.6597,
|
143 |
-
"step": 19
|
144 |
-
},
|
145 |
-
{
|
146 |
-
"epoch": 0.17467248908296942,
|
147 |
-
"grad_norm": 1.1328125,
|
148 |
-
"learning_rate": 8.636363636363637e-06,
|
149 |
-
"loss": 2.5515,
|
150 |
-
"step": 20
|
151 |
-
},
|
152 |
-
{
|
153 |
-
"epoch": 0.18340611353711792,
|
154 |
-
"grad_norm": 1.140625,
|
155 |
-
"learning_rate": 9.090909090909091e-06,
|
156 |
-
"loss": 2.5699,
|
157 |
-
"step": 21
|
158 |
-
},
|
159 |
-
{
|
160 |
-
"epoch": 0.19213973799126638,
|
161 |
-
"grad_norm": 1.1015625,
|
162 |
-
"learning_rate": 9.545454545454547e-06,
|
163 |
-
"loss": 2.6027,
|
164 |
-
"step": 22
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 0.20087336244541484,
|
168 |
-
"grad_norm": 1.109375,
|
169 |
-
"learning_rate": 1e-05,
|
170 |
-
"loss": 2.5589,
|
171 |
-
"step": 23
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"epoch": 0.2096069868995633,
|
175 |
-
"grad_norm": 1.0859375,
|
176 |
-
"learning_rate": 9.999869003890174e-06,
|
177 |
-
"loss": 2.5869,
|
178 |
-
"step": 24
|
179 |
-
},
|
180 |
-
{
|
181 |
-
"epoch": 0.2183406113537118,
|
182 |
-
"grad_norm": 1.078125,
|
183 |
-
"learning_rate": 9.999476022424688e-06,
|
184 |
-
"loss": 2.5414,
|
185 |
-
"step": 25
|
186 |
-
},
|
187 |
-
{
|
188 |
-
"epoch": 0.22707423580786026,
|
189 |
-
"grad_norm": 1.03125,
|
190 |
-
"learning_rate": 9.998821076195158e-06,
|
191 |
-
"loss": 2.6005,
|
192 |
-
"step": 26
|
193 |
-
},
|
194 |
-
{
|
195 |
-
"epoch": 0.23580786026200873,
|
196 |
-
"grad_norm": 1.078125,
|
197 |
-
"learning_rate": 9.997904199519748e-06,
|
198 |
-
"loss": 2.5769,
|
199 |
-
"step": 27
|
200 |
-
},
|
201 |
-
{
|
202 |
-
"epoch": 0.2445414847161572,
|
203 |
-
"grad_norm": 1.0703125,
|
204 |
-
"learning_rate": 9.996725440441368e-06,
|
205 |
-
"loss": 2.6084,
|
206 |
-
"step": 28
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 0.25327510917030566,
|
210 |
-
"grad_norm": 0.98828125,
|
211 |
-
"learning_rate": 9.995284860725162e-06,
|
212 |
-
"loss": 2.6237,
|
213 |
-
"step": 29
|
214 |
-
},
|
215 |
-
{
|
216 |
-
"epoch": 0.26200873362445415,
|
217 |
-
"grad_norm": 0.9453125,
|
218 |
-
"learning_rate": 9.993582535855265e-06,
|
219 |
-
"loss": 2.577,
|
220 |
-
"step": 30
|
221 |
-
},
|
222 |
-
{
|
223 |
-
"epoch": 0.27074235807860264,
|
224 |
-
"grad_norm": 0.953125,
|
225 |
-
"learning_rate": 9.991618555030848e-06,
|
226 |
-
"loss": 2.591,
|
227 |
-
"step": 31
|
228 |
-
},
|
229 |
-
{
|
230 |
-
"epoch": 0.2794759825327511,
|
231 |
-
"grad_norm": 0.94921875,
|
232 |
-
"learning_rate": 9.989393021161455e-06,
|
233 |
-
"loss": 2.5533,
|
234 |
-
"step": 32
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"epoch": 0.28820960698689957,
|
238 |
-
"grad_norm": 0.99609375,
|
239 |
-
"learning_rate": 9.986906050861595e-06,
|
240 |
-
"loss": 2.5694,
|
241 |
-
"step": 33
|
242 |
-
},
|
243 |
-
{
|
244 |
-
"epoch": 0.29694323144104806,
|
245 |
-
"grad_norm": 0.9765625,
|
246 |
-
"learning_rate": 9.98415777444464e-06,
|
247 |
-
"loss": 2.53,
|
248 |
-
"step": 34
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 0.3056768558951965,
|
252 |
-
"grad_norm": 0.9296875,
|
253 |
-
"learning_rate": 9.981148335916e-06,
|
254 |
-
"loss": 2.5486,
|
255 |
-
"step": 35
|
256 |
-
},
|
257 |
-
{
|
258 |
-
"epoch": 0.314410480349345,
|
259 |
-
"grad_norm": 0.92578125,
|
260 |
-
"learning_rate": 9.977877892965572e-06,
|
261 |
-
"loss": 2.5649,
|
262 |
-
"step": 36
|
263 |
-
},
|
264 |
-
{
|
265 |
-
"epoch": 0.3231441048034934,
|
266 |
-
"grad_norm": 0.9609375,
|
267 |
-
"learning_rate": 9.974346616959476e-06,
|
268 |
-
"loss": 2.6342,
|
269 |
-
"step": 37
|
270 |
-
},
|
271 |
-
{
|
272 |
-
"epoch": 0.3318777292576419,
|
273 |
-
"grad_norm": 0.9140625,
|
274 |
-
"learning_rate": 9.970554692931081e-06,
|
275 |
-
"loss": 2.5869,
|
276 |
-
"step": 38
|
277 |
-
},
|
278 |
-
{
|
279 |
-
"epoch": 0.3406113537117904,
|
280 |
-
"grad_norm": 0.90234375,
|
281 |
-
"learning_rate": 9.966502319571303e-06,
|
282 |
-
"loss": 2.5639,
|
283 |
-
"step": 39
|
284 |
-
},
|
285 |
-
{
|
286 |
-
"epoch": 0.34934497816593885,
|
287 |
-
"grad_norm": 0.9375,
|
288 |
-
"learning_rate": 9.962189709218202e-06,
|
289 |
-
"loss": 2.5443,
|
290 |
-
"step": 40
|
291 |
-
},
|
292 |
-
{
|
293 |
-
"epoch": 0.35807860262008734,
|
294 |
-
"grad_norm": 0.9453125,
|
295 |
-
"learning_rate": 9.95761708784585e-06,
|
296 |
-
"loss": 2.5412,
|
297 |
-
"step": 41
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"epoch": 0.36681222707423583,
|
301 |
-
"grad_norm": 0.8828125,
|
302 |
-
"learning_rate": 9.952784695052494e-06,
|
303 |
-
"loss": 2.5115,
|
304 |
-
"step": 42
|
305 |
-
},
|
306 |
-
{
|
307 |
-
"epoch": 0.37554585152838427,
|
308 |
-
"grad_norm": 0.99609375,
|
309 |
-
"learning_rate": 9.94769278404799e-06,
|
310 |
-
"loss": 2.4547,
|
311 |
-
"step": 43
|
312 |
-
},
|
313 |
-
{
|
314 |
-
"epoch": 0.38427947598253276,
|
315 |
-
"grad_norm": 0.90234375,
|
316 |
-
"learning_rate": 9.942341621640558e-06,
|
317 |
-
"loss": 2.5528,
|
318 |
-
"step": 44
|
319 |
-
},
|
320 |
-
{
|
321 |
-
"epoch": 0.3930131004366812,
|
322 |
-
"grad_norm": 0.96484375,
|
323 |
-
"learning_rate": 9.936731488222776e-06,
|
324 |
-
"loss": 2.5629,
|
325 |
-
"step": 45
|
326 |
-
},
|
327 |
-
{
|
328 |
-
"epoch": 0.4017467248908297,
|
329 |
-
"grad_norm": 0.89453125,
|
330 |
-
"learning_rate": 9.930862677756912e-06,
|
331 |
-
"loss": 2.5632,
|
332 |
-
"step": 46
|
333 |
-
},
|
334 |
-
{
|
335 |
-
"epoch": 0.4104803493449782,
|
336 |
-
"grad_norm": 0.890625,
|
337 |
-
"learning_rate": 9.924735497759497e-06,
|
338 |
-
"loss": 2.5625,
|
339 |
-
"step": 47
|
340 |
-
},
|
341 |
-
{
|
342 |
-
"epoch": 0.4192139737991266,
|
343 |
-
"grad_norm": 0.875,
|
344 |
-
"learning_rate": 9.918350269285228e-06,
|
345 |
-
"loss": 2.5522,
|
346 |
-
"step": 48
|
347 |
-
},
|
348 |
-
{
|
349 |
-
"epoch": 0.4279475982532751,
|
350 |
-
"grad_norm": 0.90234375,
|
351 |
-
"learning_rate": 9.911707326910145e-06,
|
352 |
-
"loss": 2.6349,
|
353 |
-
"step": 49
|
354 |
-
},
|
355 |
-
{
|
356 |
-
"epoch": 0.4366812227074236,
|
357 |
-
"grad_norm": 0.91015625,
|
358 |
-
"learning_rate": 9.904807018714088e-06,
|
359 |
-
"loss": 2.6174,
|
360 |
-
"step": 50
|
361 |
-
},
|
362 |
-
{
|
363 |
-
"epoch": 0.44541484716157204,
|
364 |
-
"grad_norm": 0.89453125,
|
365 |
-
"learning_rate": 9.897649706262474e-06,
|
366 |
-
"loss": 2.5732,
|
367 |
-
"step": 51
|
368 |
-
},
|
369 |
-
{
|
370 |
-
"epoch": 0.45414847161572053,
|
371 |
-
"grad_norm": 0.91796875,
|
372 |
-
"learning_rate": 9.890235764587332e-06,
|
373 |
-
"loss": 2.6071,
|
374 |
-
"step": 52
|
375 |
-
},
|
376 |
-
{
|
377 |
-
"epoch": 0.462882096069869,
|
378 |
-
"grad_norm": 0.89453125,
|
379 |
-
"learning_rate": 9.882565582167673e-06,
|
380 |
-
"loss": 2.5587,
|
381 |
-
"step": 53
|
382 |
-
},
|
383 |
-
{
|
384 |
-
"epoch": 0.47161572052401746,
|
385 |
-
"grad_norm": 0.88671875,
|
386 |
-
"learning_rate": 9.874639560909118e-06,
|
387 |
-
"loss": 2.5676,
|
388 |
-
"step": 54
|
389 |
-
},
|
390 |
-
{
|
391 |
-
"epoch": 0.48034934497816595,
|
392 |
-
"grad_norm": 0.890625,
|
393 |
-
"learning_rate": 9.866458116122852e-06,
|
394 |
-
"loss": 2.515,
|
395 |
-
"step": 55
|
396 |
-
},
|
397 |
-
{
|
398 |
-
"epoch": 0.4890829694323144,
|
399 |
-
"grad_norm": 0.8984375,
|
400 |
-
"learning_rate": 9.858021676503846e-06,
|
401 |
-
"loss": 2.5355,
|
402 |
-
"step": 56
|
403 |
-
},
|
404 |
-
{
|
405 |
-
"epoch": 0.4978165938864629,
|
406 |
-
"grad_norm": 0.90234375,
|
407 |
-
"learning_rate": 9.849330684108409e-06,
|
408 |
-
"loss": 2.5798,
|
409 |
-
"step": 57
|
410 |
-
},
|
411 |
-
{
|
412 |
-
"epoch": 0.5065502183406113,
|
413 |
-
"grad_norm": 0.87890625,
|
414 |
-
"learning_rate": 9.840385594331022e-06,
|
415 |
-
"loss": 2.5391,
|
416 |
-
"step": 58
|
417 |
-
},
|
418 |
-
{
|
419 |
-
"epoch": 0.5152838427947598,
|
420 |
-
"grad_norm": 0.90625,
|
421 |
-
"learning_rate": 9.831186875880467e-06,
|
422 |
-
"loss": 2.521,
|
423 |
-
"step": 59
|
424 |
-
},
|
425 |
-
{
|
426 |
-
"epoch": 0.5240174672489083,
|
427 |
-
"grad_norm": 0.91796875,
|
428 |
-
"learning_rate": 9.82173501075528e-06,
|
429 |
-
"loss": 2.5553,
|
430 |
-
"step": 60
|
431 |
-
},
|
432 |
-
{
|
433 |
-
"epoch": 0.5327510917030568,
|
434 |
-
"grad_norm": 0.890625,
|
435 |
-
"learning_rate": 9.812030494218484e-06,
|
436 |
-
"loss": 2.6096,
|
437 |
-
"step": 61
|
438 |
-
},
|
439 |
-
{
|
440 |
-
"epoch": 0.5414847161572053,
|
441 |
-
"grad_norm": 0.88671875,
|
442 |
-
"learning_rate": 9.802073834771642e-06,
|
443 |
-
"loss": 2.5513,
|
444 |
-
"step": 62
|
445 |
-
},
|
446 |
-
{
|
447 |
-
"epoch": 0.5502183406113537,
|
448 |
-
"grad_norm": 0.96484375,
|
449 |
-
"learning_rate": 9.79186555412822e-06,
|
450 |
-
"loss": 2.6127,
|
451 |
-
"step": 63
|
452 |
-
},
|
453 |
-
{
|
454 |
-
"epoch": 0.5589519650655022,
|
455 |
-
"grad_norm": 0.90234375,
|
456 |
-
"learning_rate": 9.781406187186237e-06,
|
457 |
-
"loss": 2.5172,
|
458 |
-
"step": 64
|
459 |
-
},
|
460 |
-
{
|
461 |
-
"epoch": 0.5676855895196506,
|
462 |
-
"grad_norm": 0.87890625,
|
463 |
-
"learning_rate": 9.770696282000245e-06,
|
464 |
-
"loss": 2.5562,
|
465 |
-
"step": 65
|
466 |
-
},
|
467 |
-
{
|
468 |
-
"epoch": 0.5764192139737991,
|
469 |
-
"grad_norm": 0.88671875,
|
470 |
-
"learning_rate": 9.759736399752611e-06,
|
471 |
-
"loss": 2.5538,
|
472 |
-
"step": 66
|
473 |
-
},
|
474 |
-
{
|
475 |
-
"epoch": 0.5851528384279476,
|
476 |
-
"grad_norm": 0.89453125,
|
477 |
-
"learning_rate": 9.748527114724111e-06,
|
478 |
-
"loss": 2.5661,
|
479 |
-
"step": 67
|
480 |
-
},
|
481 |
-
{
|
482 |
-
"epoch": 0.5938864628820961,
|
483 |
-
"grad_norm": 0.91796875,
|
484 |
-
"learning_rate": 9.737069014263837e-06,
|
485 |
-
"loss": 2.6247,
|
486 |
-
"step": 68
|
487 |
-
},
|
488 |
-
{
|
489 |
-
"epoch": 0.6026200873362445,
|
490 |
-
"grad_norm": 0.9296875,
|
491 |
-
"learning_rate": 9.725362698758425e-06,
|
492 |
-
"loss": 2.5432,
|
493 |
-
"step": 69
|
494 |
-
},
|
495 |
-
{
|
496 |
-
"epoch": 0.611353711790393,
|
497 |
-
"grad_norm": 0.890625,
|
498 |
-
"learning_rate": 9.713408781600588e-06,
|
499 |
-
"loss": 2.51,
|
500 |
-
"step": 70
|
501 |
-
},
|
502 |
-
{
|
503 |
-
"epoch": 0.6200873362445415,
|
504 |
-
"grad_norm": 0.8828125,
|
505 |
-
"learning_rate": 9.701207889156989e-06,
|
506 |
-
"loss": 2.5114,
|
507 |
-
"step": 71
|
508 |
-
},
|
509 |
-
{
|
510 |
-
"epoch": 0.62882096069869,
|
511 |
-
"grad_norm": 0.9296875,
|
512 |
-
"learning_rate": 9.688760660735403e-06,
|
513 |
-
"loss": 2.5707,
|
514 |
-
"step": 72
|
515 |
-
},
|
516 |
-
{
|
517 |
-
"epoch": 0.6375545851528385,
|
518 |
-
"grad_norm": 0.91015625,
|
519 |
-
"learning_rate": 9.676067748551232e-06,
|
520 |
-
"loss": 2.579,
|
521 |
-
"step": 73
|
522 |
-
},
|
523 |
-
{
|
524 |
-
"epoch": 0.6462882096069869,
|
525 |
-
"grad_norm": 0.91015625,
|
526 |
-
"learning_rate": 9.663129817693323e-06,
|
527 |
-
"loss": 2.5844,
|
528 |
-
"step": 74
|
529 |
-
},
|
530 |
-
{
|
531 |
-
"epoch": 0.6550218340611353,
|
532 |
-
"grad_norm": 0.9296875,
|
533 |
-
"learning_rate": 9.64994754608912e-06,
|
534 |
-
"loss": 2.5768,
|
535 |
-
"step": 75
|
536 |
-
},
|
537 |
-
{
|
538 |
-
"epoch": 0.6637554585152838,
|
539 |
-
"grad_norm": 0.890625,
|
540 |
-
"learning_rate": 9.636521624469144e-06,
|
541 |
-
"loss": 2.5568,
|
542 |
-
"step": 76
|
543 |
-
},
|
544 |
-
{
|
545 |
-
"epoch": 0.6724890829694323,
|
546 |
-
"grad_norm": 0.91796875,
|
547 |
-
"learning_rate": 9.622852756330797e-06,
|
548 |
-
"loss": 2.5348,
|
549 |
-
"step": 77
|
550 |
-
},
|
551 |
-
{
|
552 |
-
"epoch": 0.6812227074235808,
|
553 |
-
"grad_norm": 0.88671875,
|
554 |
-
"learning_rate": 9.608941657901496e-06,
|
555 |
-
"loss": 2.5221,
|
556 |
-
"step": 78
|
557 |
-
},
|
558 |
-
{
|
559 |
-
"epoch": 0.6899563318777293,
|
560 |
-
"grad_norm": 0.921875,
|
561 |
-
"learning_rate": 9.594789058101154e-06,
|
562 |
-
"loss": 2.6385,
|
563 |
-
"step": 79
|
564 |
-
},
|
565 |
-
{
|
566 |
-
"epoch": 0.6986899563318777,
|
567 |
-
"grad_norm": 0.91796875,
|
568 |
-
"learning_rate": 9.580395698503979e-06,
|
569 |
-
"loss": 2.5107,
|
570 |
-
"step": 80
|
571 |
-
},
|
572 |
-
{
|
573 |
-
"epoch": 0.7074235807860262,
|
574 |
-
"grad_norm": 0.953125,
|
575 |
-
"learning_rate": 9.565762333299616e-06,
|
576 |
-
"loss": 2.5751,
|
577 |
-
"step": 81
|
578 |
-
},
|
579 |
-
{
|
580 |
-
"epoch": 0.7161572052401747,
|
581 |
-
"grad_norm": 0.93359375,
|
582 |
-
"learning_rate": 9.550889729253631e-06,
|
583 |
-
"loss": 2.6106,
|
584 |
-
"step": 82
|
585 |
-
},
|
586 |
-
{
|
587 |
-
"epoch": 0.7248908296943232,
|
588 |
-
"grad_norm": 0.921875,
|
589 |
-
"learning_rate": 9.535778665667334e-06,
|
590 |
-
"loss": 2.6177,
|
591 |
-
"step": 83
|
592 |
-
},
|
593 |
-
{
|
594 |
-
"epoch": 0.7336244541484717,
|
595 |
-
"grad_norm": 1.0,
|
596 |
-
"learning_rate": 9.520429934336944e-06,
|
597 |
-
"loss": 2.5421,
|
598 |
-
"step": 84
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"epoch": 0.74235807860262,
|
602 |
-
"grad_norm": 0.90234375,
|
603 |
-
"learning_rate": 9.504844339512096e-06,
|
604 |
-
"loss": 2.6234,
|
605 |
-
"step": 85
|
606 |
-
},
|
607 |
-
{
|
608 |
-
"epoch": 0.7510917030567685,
|
609 |
-
"grad_norm": 0.91015625,
|
610 |
-
"learning_rate": 9.48902269785371e-06,
|
611 |
-
"loss": 2.5791,
|
612 |
-
"step": 86
|
613 |
-
},
|
614 |
-
{
|
615 |
-
"epoch": 0.759825327510917,
|
616 |
-
"grad_norm": 0.8671875,
|
617 |
-
"learning_rate": 9.472965838391187e-06,
|
618 |
-
"loss": 2.5052,
|
619 |
-
"step": 87
|
620 |
-
},
|
621 |
-
{
|
622 |
-
"epoch": 0.7685589519650655,
|
623 |
-
"grad_norm": 0.984375,
|
624 |
-
"learning_rate": 9.456674602478975e-06,
|
625 |
-
"loss": 2.5445,
|
626 |
-
"step": 88
|
627 |
-
},
|
628 |
-
{
|
629 |
-
"epoch": 0.777292576419214,
|
630 |
-
"grad_norm": 1.1953125,
|
631 |
-
"learning_rate": 9.44014984375249e-06,
|
632 |
-
"loss": 2.5956,
|
633 |
-
"step": 89
|
634 |
-
},
|
635 |
-
{
|
636 |
-
"epoch": 0.7860262008733624,
|
637 |
-
"grad_norm": 0.87109375,
|
638 |
-
"learning_rate": 9.423392428083374e-06,
|
639 |
-
"loss": 2.5261,
|
640 |
-
"step": 90
|
641 |
-
},
|
642 |
-
{
|
643 |
-
"epoch": 0.7947598253275109,
|
644 |
-
"grad_norm": 0.89453125,
|
645 |
-
"learning_rate": 9.406403233534134e-06,
|
646 |
-
"loss": 2.5626,
|
647 |
-
"step": 91
|
648 |
-
},
|
649 |
-
{
|
650 |
-
"epoch": 0.8034934497816594,
|
651 |
-
"grad_norm": 0.89453125,
|
652 |
-
"learning_rate": 9.389183150312124e-06,
|
653 |
-
"loss": 2.5228,
|
654 |
-
"step": 92
|
655 |
-
},
|
656 |
-
{
|
657 |
-
"epoch": 0.8122270742358079,
|
658 |
-
"grad_norm": 0.875,
|
659 |
-
"learning_rate": 9.371733080722911e-06,
|
660 |
-
"loss": 2.5494,
|
661 |
-
"step": 93
|
662 |
-
},
|
663 |
-
{
|
664 |
-
"epoch": 0.8209606986899564,
|
665 |
-
"grad_norm": 0.93359375,
|
666 |
-
"learning_rate": 9.354053939122988e-06,
|
667 |
-
"loss": 2.6738,
|
668 |
-
"step": 94
|
669 |
-
},
|
670 |
-
{
|
671 |
-
"epoch": 0.8296943231441049,
|
672 |
-
"grad_norm": 0.91015625,
|
673 |
-
"learning_rate": 9.33614665187187e-06,
|
674 |
-
"loss": 2.5862,
|
675 |
-
"step": 95
|
676 |
-
},
|
677 |
-
{
|
678 |
-
"epoch": 0.8384279475982532,
|
679 |
-
"grad_norm": 0.91015625,
|
680 |
-
"learning_rate": 9.318012157283533e-06,
|
681 |
-
"loss": 2.57,
|
682 |
-
"step": 96
|
683 |
-
},
|
684 |
-
{
|
685 |
-
"epoch": 0.8471615720524017,
|
686 |
-
"grad_norm": 0.96875,
|
687 |
-
"learning_rate": 9.299651405577286e-06,
|
688 |
-
"loss": 2.6046,
|
689 |
-
"step": 97
|
690 |
-
},
|
691 |
-
{
|
692 |
-
"epoch": 0.8558951965065502,
|
693 |
-
"grad_norm": 0.9140625,
|
694 |
-
"learning_rate": 9.28106535882794e-06,
|
695 |
-
"loss": 2.5911,
|
696 |
-
"step": 98
|
697 |
-
},
|
698 |
-
{
|
699 |
-
"epoch": 0.8646288209606987,
|
700 |
-
"grad_norm": 0.90234375,
|
701 |
-
"learning_rate": 9.262254990915427e-06,
|
702 |
-
"loss": 2.5898,
|
703 |
-
"step": 99
|
704 |
-
},
|
705 |
-
{
|
706 |
-
"epoch": 0.8733624454148472,
|
707 |
-
"grad_norm": 0.93359375,
|
708 |
-
"learning_rate": 9.243221287473755e-06,
|
709 |
-
"loss": 2.6268,
|
710 |
-
"step": 100
|
711 |
-
},
|
712 |
-
{
|
713 |
-
"epoch": 0.8820960698689956,
|
714 |
-
"grad_norm": 0.91015625,
|
715 |
-
"learning_rate": 9.223965245839367e-06,
|
716 |
-
"loss": 2.5823,
|
717 |
-
"step": 101
|
718 |
-
},
|
719 |
-
{
|
720 |
-
"epoch": 0.8908296943231441,
|
721 |
-
"grad_norm": 0.91796875,
|
722 |
-
"learning_rate": 9.20448787499888e-06,
|
723 |
-
"loss": 2.6937,
|
724 |
-
"step": 102
|
725 |
-
},
|
726 |
-
{
|
727 |
-
"epoch": 0.8995633187772926,
|
728 |
-
"grad_norm": 0.9296875,
|
729 |
-
"learning_rate": 9.184790195536217e-06,
|
730 |
-
"loss": 2.5609,
|
731 |
-
"step": 103
|
732 |
-
},
|
733 |
-
{
|
734 |
-
"epoch": 0.9082969432314411,
|
735 |
-
"grad_norm": 0.91015625,
|
736 |
-
"learning_rate": 9.164873239579133e-06,
|
737 |
-
"loss": 2.5716,
|
738 |
-
"step": 104
|
739 |
-
},
|
740 |
-
{
|
741 |
-
"epoch": 0.9170305676855895,
|
742 |
-
"grad_norm": 0.99609375,
|
743 |
-
"learning_rate": 9.144738050745129e-06,
|
744 |
-
"loss": 2.5099,
|
745 |
-
"step": 105
|
746 |
-
},
|
747 |
-
{
|
748 |
-
"epoch": 0.925764192139738,
|
749 |
-
"grad_norm": 0.91015625,
|
750 |
-
"learning_rate": 9.124385684086762e-06,
|
751 |
-
"loss": 2.5131,
|
752 |
-
"step": 106
|
753 |
-
},
|
754 |
-
{
|
755 |
-
"epoch": 0.9344978165938864,
|
756 |
-
"grad_norm": 1.015625,
|
757 |
-
"learning_rate": 9.103817206036383e-06,
|
758 |
-
"loss": 2.5407,
|
759 |
-
"step": 107
|
760 |
-
},
|
761 |
-
{
|
762 |
-
"epoch": 0.9432314410480349,
|
763 |
-
"grad_norm": 0.9609375,
|
764 |
-
"learning_rate": 9.08303369435023e-06,
|
765 |
-
"loss": 2.5364,
|
766 |
-
"step": 108
|
767 |
-
},
|
768 |
-
{
|
769 |
-
"epoch": 0.9519650655021834,
|
770 |
-
"grad_norm": 0.9296875,
|
771 |
-
"learning_rate": 9.062036238051978e-06,
|
772 |
-
"loss": 2.6053,
|
773 |
-
"step": 109
|
774 |
-
},
|
775 |
-
{
|
776 |
-
"epoch": 0.9606986899563319,
|
777 |
-
"grad_norm": 0.9296875,
|
778 |
-
"learning_rate": 9.040825937375664e-06,
|
779 |
-
"loss": 2.563,
|
780 |
-
"step": 110
|
781 |
-
},
|
782 |
-
{
|
783 |
-
"epoch": 0.9694323144104804,
|
784 |
-
"grad_norm": 0.9375,
|
785 |
-
"learning_rate": 9.019403903708036e-06,
|
786 |
-
"loss": 2.5744,
|
787 |
-
"step": 111
|
788 |
-
},
|
789 |
-
{
|
790 |
-
"epoch": 0.9781659388646288,
|
791 |
-
"grad_norm": 0.93359375,
|
792 |
-
"learning_rate": 8.997771259530324e-06,
|
793 |
-
"loss": 2.5768,
|
794 |
-
"step": 112
|
795 |
-
},
|
796 |
-
{
|
797 |
-
"epoch": 0.9868995633187773,
|
798 |
-
"grad_norm": 0.96484375,
|
799 |
-
"learning_rate": 8.975929138359423e-06,
|
800 |
-
"loss": 2.577,
|
801 |
-
"step": 113
|
802 |
-
},
|
803 |
-
{
|
804 |
-
"epoch": 0.9956331877729258,
|
805 |
-
"grad_norm": 0.92578125,
|
806 |
-
"learning_rate": 8.953878684688492e-06,
|
807 |
-
"loss": 2.6206,
|
808 |
-
"step": 114
|
809 |
-
},
|
810 |
-
{
|
811 |
-
"epoch": 1.0,
|
812 |
-
"grad_norm": 1.8828125,
|
813 |
-
"learning_rate": 8.931621053926998e-06,
|
814 |
-
"loss": 2.5724,
|
815 |
-
"step": 115
|
816 |
-
},
|
817 |
-
{
|
818 |
-
"epoch": 1.0087336244541485,
|
819 |
-
"grad_norm": 0.87890625,
|
820 |
-
"learning_rate": 8.90915741234015e-06,
|
821 |
-
"loss": 2.4993,
|
822 |
-
"step": 116
|
823 |
-
},
|
824 |
-
{
|
825 |
-
"epoch": 1.017467248908297,
|
826 |
-
"grad_norm": 0.9296875,
|
827 |
-
"learning_rate": 8.886488936987817e-06,
|
828 |
-
"loss": 2.5537,
|
829 |
-
"step": 117
|
830 |
-
},
|
831 |
-
{
|
832 |
-
"epoch": 1.0262008733624455,
|
833 |
-
"grad_norm": 0.93359375,
|
834 |
-
"learning_rate": 8.863616815662833e-06,
|
835 |
-
"loss": 2.6468,
|
836 |
-
"step": 118
|
837 |
-
},
|
838 |
-
{
|
839 |
-
"epoch": 1.034934497816594,
|
840 |
-
"grad_norm": 0.91796875,
|
841 |
-
"learning_rate": 8.840542246828763e-06,
|
842 |
-
"loss": 2.5739,
|
843 |
-
"step": 119
|
844 |
-
},
|
845 |
-
{
|
846 |
-
"epoch": 1.0436681222707425,
|
847 |
-
"grad_norm": 0.96484375,
|
848 |
-
"learning_rate": 8.817266439557109e-06,
|
849 |
-
"loss": 2.5705,
|
850 |
-
"step": 120
|
851 |
-
},
|
852 |
-
{
|
853 |
-
"epoch": 1.0524017467248907,
|
854 |
-
"grad_norm": 0.89453125,
|
855 |
-
"learning_rate": 8.793790613463956e-06,
|
856 |
-
"loss": 2.587,
|
857 |
-
"step": 121
|
858 |
-
},
|
859 |
-
{
|
860 |
-
"epoch": 1.0611353711790392,
|
861 |
-
"grad_norm": 0.88671875,
|
862 |
-
"learning_rate": 8.770115998646057e-06,
|
863 |
-
"loss": 2.522,
|
864 |
-
"step": 122
|
865 |
-
},
|
866 |
-
{
|
867 |
-
"epoch": 1.0698689956331877,
|
868 |
-
"grad_norm": 0.91015625,
|
869 |
-
"learning_rate": 8.746243835616392e-06,
|
870 |
-
"loss": 2.5717,
|
871 |
-
"step": 123
|
872 |
-
},
|
873 |
-
{
|
874 |
-
"epoch": 1.0786026200873362,
|
875 |
-
"grad_norm": 0.92578125,
|
876 |
-
"learning_rate": 8.722175375239157e-06,
|
877 |
-
"loss": 2.5287,
|
878 |
-
"step": 124
|
879 |
-
},
|
880 |
-
{
|
881 |
-
"epoch": 1.0873362445414847,
|
882 |
-
"grad_norm": 0.8828125,
|
883 |
-
"learning_rate": 8.697911878664222e-06,
|
884 |
-
"loss": 2.4822,
|
885 |
-
"step": 125
|
886 |
-
},
|
887 |
-
{
|
888 |
-
"epoch": 1.0960698689956332,
|
889 |
-
"grad_norm": 0.9296875,
|
890 |
-
"learning_rate": 8.673454617261054e-06,
|
891 |
-
"loss": 2.5232,
|
892 |
-
"step": 126
|
893 |
-
},
|
894 |
-
{
|
895 |
-
"epoch": 1.1048034934497817,
|
896 |
-
"grad_norm": 0.87890625,
|
897 |
-
"learning_rate": 8.648804872552092e-06,
|
898 |
-
"loss": 2.5506,
|
899 |
-
"step": 127
|
900 |
-
},
|
901 |
-
{
|
902 |
-
"epoch": 1.1135371179039302,
|
903 |
-
"grad_norm": 0.8984375,
|
904 |
-
"learning_rate": 8.6239639361456e-06,
|
905 |
-
"loss": 2.6104,
|
906 |
-
"step": 128
|
907 |
-
},
|
908 |
-
{
|
909 |
-
"epoch": 1.1222707423580787,
|
910 |
-
"grad_norm": 0.95703125,
|
911 |
-
"learning_rate": 8.598933109667995e-06,
|
912 |
-
"loss": 2.642,
|
913 |
-
"step": 129
|
914 |
-
},
|
915 |
-
{
|
916 |
-
"epoch": 1.1310043668122272,
|
917 |
-
"grad_norm": 0.90625,
|
918 |
-
"learning_rate": 8.573713704695633e-06,
|
919 |
-
"loss": 2.5569,
|
920 |
-
"step": 130
|
921 |
-
},
|
922 |
-
{
|
923 |
-
"epoch": 1.1397379912663754,
|
924 |
-
"grad_norm": 0.91796875,
|
925 |
-
"learning_rate": 8.548307042686093e-06,
|
926 |
-
"loss": 2.567,
|
927 |
-
"step": 131
|
928 |
-
},
|
929 |
-
{
|
930 |
-
"epoch": 1.1484716157205241,
|
931 |
-
"grad_norm": 0.90625,
|
932 |
-
"learning_rate": 8.522714454908926e-06,
|
933 |
-
"loss": 2.5177,
|
934 |
-
"step": 132
|
935 |
-
},
|
936 |
-
{
|
937 |
-
"epoch": 1.1572052401746724,
|
938 |
-
"grad_norm": 0.91796875,
|
939 |
-
"learning_rate": 8.496937282375912e-06,
|
940 |
-
"loss": 2.5793,
|
941 |
-
"step": 133
|
942 |
-
},
|
943 |
-
{
|
944 |
-
"epoch": 1.165938864628821,
|
945 |
-
"grad_norm": 0.8984375,
|
946 |
-
"learning_rate": 8.470976875770776e-06,
|
947 |
-
"loss": 2.543,
|
948 |
-
"step": 134
|
949 |
-
},
|
950 |
-
{
|
951 |
-
"epoch": 1.1746724890829694,
|
952 |
-
"grad_norm": 0.90625,
|
953 |
-
"learning_rate": 8.444834595378434e-06,
|
954 |
-
"loss": 2.5375,
|
955 |
-
"step": 135
|
956 |
-
},
|
957 |
-
{
|
958 |
-
"epoch": 1.1834061135371179,
|
959 |
-
"grad_norm": 0.92578125,
|
960 |
-
"learning_rate": 8.418511811013694e-06,
|
961 |
-
"loss": 2.5851,
|
962 |
-
"step": 136
|
963 |
-
},
|
964 |
-
{
|
965 |
-
"epoch": 1.1921397379912664,
|
966 |
-
"grad_norm": 0.91796875,
|
967 |
-
"learning_rate": 8.3920099019495e-06,
|
968 |
-
"loss": 2.6014,
|
969 |
-
"step": 137
|
970 |
-
},
|
971 |
-
{
|
972 |
-
"epoch": 1.2008733624454149,
|
973 |
-
"grad_norm": 1.0078125,
|
974 |
-
"learning_rate": 8.365330256844647e-06,
|
975 |
-
"loss": 2.5553,
|
976 |
-
"step": 138
|
977 |
-
},
|
978 |
-
{
|
979 |
-
"epoch": 1.2096069868995634,
|
980 |
-
"grad_norm": 0.91796875,
|
981 |
-
"learning_rate": 8.33847427367102e-06,
|
982 |
-
"loss": 2.5817,
|
983 |
-
"step": 139
|
984 |
-
},
|
985 |
-
{
|
986 |
-
"epoch": 1.2183406113537119,
|
987 |
-
"grad_norm": 0.9609375,
|
988 |
-
"learning_rate": 8.311443359640353e-06,
|
989 |
-
"loss": 2.5187,
|
990 |
-
"step": 140
|
991 |
-
},
|
992 |
-
{
|
993 |
-
"epoch": 1.2270742358078603,
|
994 |
-
"grad_norm": 0.921875,
|
995 |
-
"learning_rate": 8.284238931130476e-06,
|
996 |
-
"loss": 2.5306,
|
997 |
-
"step": 141
|
998 |
-
},
|
999 |
-
{
|
1000 |
-
"epoch": 1.2358078602620086,
|
1001 |
-
"grad_norm": 0.91796875,
|
1002 |
-
"learning_rate": 8.256862413611113e-06,
|
1003 |
-
"loss": 2.56,
|
1004 |
-
"step": 142
|
1005 |
-
},
|
1006 |
-
{
|
1007 |
-
"epoch": 1.244541484716157,
|
1008 |
-
"grad_norm": 0.953125,
|
1009 |
-
"learning_rate": 8.229315241569177e-06,
|
1010 |
-
"loss": 2.5076,
|
1011 |
-
"step": 143
|
1012 |
-
},
|
1013 |
-
{
|
1014 |
-
"epoch": 1.2532751091703056,
|
1015 |
-
"grad_norm": 0.94921875,
|
1016 |
-
"learning_rate": 8.201598858433625e-06,
|
1017 |
-
"loss": 2.5798,
|
1018 |
-
"step": 144
|
1019 |
-
},
|
1020 |
-
{
|
1021 |
-
"epoch": 1.262008733624454,
|
1022 |
-
"grad_norm": 0.8671875,
|
1023 |
-
"learning_rate": 8.173714716499801e-06,
|
1024 |
-
"loss": 2.4532,
|
1025 |
-
"step": 145
|
1026 |
-
},
|
1027 |
-
{
|
1028 |
-
"epoch": 1.2707423580786026,
|
1029 |
-
"grad_norm": 0.94140625,
|
1030 |
-
"learning_rate": 8.145664276853353e-06,
|
1031 |
-
"loss": 2.4997,
|
1032 |
-
"step": 146
|
1033 |
-
},
|
1034 |
-
{
|
1035 |
-
"epoch": 1.279475982532751,
|
1036 |
-
"grad_norm": 0.94140625,
|
1037 |
-
"learning_rate": 8.117449009293668e-06,
|
1038 |
-
"loss": 2.5093,
|
1039 |
-
"step": 147
|
1040 |
-
},
|
1041 |
-
{
|
1042 |
-
"epoch": 1.2882096069868996,
|
1043 |
-
"grad_norm": 0.94140625,
|
1044 |
-
"learning_rate": 8.089070392256866e-06,
|
1045 |
-
"loss": 2.5558,
|
1046 |
-
"step": 148
|
1047 |
-
},
|
1048 |
-
{
|
1049 |
-
"epoch": 1.296943231441048,
|
1050 |
-
"grad_norm": 0.984375,
|
1051 |
-
"learning_rate": 8.060529912738316e-06,
|
1052 |
-
"loss": 2.5583,
|
1053 |
-
"step": 149
|
1054 |
-
},
|
1055 |
-
{
|
1056 |
-
"epoch": 1.3056768558951966,
|
1057 |
-
"grad_norm": 1.0,
|
1058 |
-
"learning_rate": 8.031829066214735e-06,
|
1059 |
-
"loss": 2.5477,
|
1060 |
-
"step": 150
|
1061 |
-
},
|
1062 |
-
{
|
1063 |
-
"epoch": 1.314410480349345,
|
1064 |
-
"grad_norm": 0.953125,
|
1065 |
-
"learning_rate": 8.002969356565822e-06,
|
1066 |
-
"loss": 2.56,
|
1067 |
-
"step": 151
|
1068 |
-
},
|
1069 |
-
{
|
1070 |
-
"epoch": 1.3231441048034935,
|
1071 |
-
"grad_norm": 0.97265625,
|
1072 |
-
"learning_rate": 7.973952295995452e-06,
|
1073 |
-
"loss": 2.5918,
|
1074 |
-
"step": 152
|
1075 |
-
},
|
1076 |
-
{
|
1077 |
-
"epoch": 1.3318777292576418,
|
1078 |
-
"grad_norm": 0.94140625,
|
1079 |
-
"learning_rate": 7.94477940495245e-06,
|
1080 |
-
"loss": 2.5883,
|
1081 |
-
"step": 153
|
1082 |
-
},
|
1083 |
-
{
|
1084 |
-
"epoch": 1.3406113537117905,
|
1085 |
-
"grad_norm": 0.9765625,
|
1086 |
-
"learning_rate": 7.91545221205091e-06,
|
1087 |
-
"loss": 2.557,
|
1088 |
-
"step": 154
|
1089 |
-
},
|
1090 |
-
{
|
1091 |
-
"epoch": 1.3493449781659388,
|
1092 |
-
"grad_norm": 0.921875,
|
1093 |
-
"learning_rate": 7.885972253990104e-06,
|
1094 |
-
"loss": 2.5619,
|
1095 |
-
"step": 155
|
1096 |
-
},
|
1097 |
-
{
|
1098 |
-
"epoch": 1.3580786026200873,
|
1099 |
-
"grad_norm": 0.93359375,
|
1100 |
-
"learning_rate": 7.856341075473963e-06,
|
1101 |
-
"loss": 2.6278,
|
1102 |
-
"step": 156
|
1103 |
-
},
|
1104 |
-
{
|
1105 |
-
"epoch": 1.3668122270742358,
|
1106 |
-
"grad_norm": 0.9453125,
|
1107 |
-
"learning_rate": 7.826560229130132e-06,
|
1108 |
-
"loss": 2.5959,
|
1109 |
-
"step": 157
|
1110 |
-
},
|
1111 |
-
{
|
1112 |
-
"epoch": 1.3755458515283843,
|
1113 |
-
"grad_norm": 0.94140625,
|
1114 |
-
"learning_rate": 7.796631275428617e-06,
|
1115 |
-
"loss": 2.529,
|
1116 |
-
"step": 158
|
1117 |
-
},
|
1118 |
-
{
|
1119 |
-
"epoch": 1.3842794759825328,
|
1120 |
-
"grad_norm": 0.91015625,
|
1121 |
-
"learning_rate": 7.766555782600023e-06,
|
1122 |
-
"loss": 2.5481,
|
1123 |
-
"step": 159
|
1124 |
-
},
|
1125 |
-
{
|
1126 |
-
"epoch": 1.3930131004366813,
|
1127 |
-
"grad_norm": 0.99609375,
|
1128 |
-
"learning_rate": 7.736335326553373e-06,
|
1129 |
-
"loss": 2.4771,
|
1130 |
-
"step": 160
|
1131 |
-
},
|
1132 |
-
{
|
1133 |
-
"epoch": 1.4017467248908297,
|
1134 |
-
"grad_norm": 0.98046875,
|
1135 |
-
"learning_rate": 7.70597149079354e-06,
|
1136 |
-
"loss": 2.5304,
|
1137 |
-
"step": 161
|
1138 |
-
},
|
1139 |
-
{
|
1140 |
-
"epoch": 1.4104803493449782,
|
1141 |
-
"grad_norm": 0.9140625,
|
1142 |
-
"learning_rate": 7.67546586633827e-06,
|
1143 |
-
"loss": 2.47,
|
1144 |
-
"step": 162
|
1145 |
-
},
|
1146 |
-
{
|
1147 |
-
"epoch": 1.4192139737991267,
|
1148 |
-
"grad_norm": 0.921875,
|
1149 |
-
"learning_rate": 7.644820051634813e-06,
|
1150 |
-
"loss": 2.5756,
|
1151 |
-
"step": 163
|
1152 |
-
},
|
1153 |
-
{
|
1154 |
-
"epoch": 1.427947598253275,
|
1155 |
-
"grad_norm": 0.9375,
|
1156 |
-
"learning_rate": 7.614035652476175e-06,
|
1157 |
-
"loss": 2.5157,
|
1158 |
-
"step": 164
|
1159 |
-
},
|
1160 |
-
{
|
1161 |
-
"epoch": 1.4366812227074237,
|
1162 |
-
"grad_norm": 0.9453125,
|
1163 |
-
"learning_rate": 7.5831142819169664e-06,
|
1164 |
-
"loss": 2.5364,
|
1165 |
-
"step": 165
|
1166 |
-
},
|
1167 |
-
{
|
1168 |
-
"epoch": 1.445414847161572,
|
1169 |
-
"grad_norm": 0.93359375,
|
1170 |
-
"learning_rate": 7.552057560188892e-06,
|
1171 |
-
"loss": 2.5279,
|
1172 |
-
"step": 166
|
1173 |
-
},
|
1174 |
-
{
|
1175 |
-
"epoch": 1.4541484716157205,
|
1176 |
-
"grad_norm": 0.90234375,
|
1177 |
-
"learning_rate": 7.520867114615844e-06,
|
1178 |
-
"loss": 2.491,
|
1179 |
-
"step": 167
|
1180 |
-
},
|
1181 |
-
{
|
1182 |
-
"epoch": 1.462882096069869,
|
1183 |
-
"grad_norm": 0.9140625,
|
1184 |
-
"learning_rate": 7.4895445795286325e-06,
|
1185 |
-
"loss": 2.5906,
|
1186 |
-
"step": 168
|
1187 |
-
},
|
1188 |
-
{
|
1189 |
-
"epoch": 1.4716157205240175,
|
1190 |
-
"grad_norm": 0.953125,
|
1191 |
-
"learning_rate": 7.458091596179359e-06,
|
1192 |
-
"loss": 2.5283,
|
1193 |
-
"step": 169
|
1194 |
-
},
|
1195 |
-
{
|
1196 |
-
"epoch": 1.480349344978166,
|
1197 |
-
"grad_norm": 1.0078125,
|
1198 |
-
"learning_rate": 7.4265098126554065e-06,
|
1199 |
-
"loss": 2.5956,
|
1200 |
-
"step": 170
|
1201 |
-
},
|
1202 |
-
{
|
1203 |
-
"epoch": 1.4890829694323144,
|
1204 |
-
"grad_norm": 0.93359375,
|
1205 |
-
"learning_rate": 7.394800883793087e-06,
|
1206 |
-
"loss": 2.5629,
|
1207 |
-
"step": 171
|
1208 |
-
},
|
1209 |
-
{
|
1210 |
-
"epoch": 1.497816593886463,
|
1211 |
-
"grad_norm": 1.0390625,
|
1212 |
-
"learning_rate": 7.3629664710909354e-06,
|
1213 |
-
"loss": 2.5138,
|
1214 |
-
"step": 172
|
1215 |
-
},
|
1216 |
-
{
|
1217 |
-
"epoch": 1.5065502183406112,
|
1218 |
-
"grad_norm": 1.0625,
|
1219 |
-
"learning_rate": 7.331008242622637e-06,
|
1220 |
-
"loss": 2.5712,
|
1221 |
-
"step": 173
|
1222 |
-
},
|
1223 |
-
{
|
1224 |
-
"epoch": 1.51528384279476,
|
1225 |
-
"grad_norm": 0.96484375,
|
1226 |
-
"learning_rate": 7.2989278729496374e-06,
|
1227 |
-
"loss": 2.6415,
|
1228 |
-
"step": 174
|
1229 |
-
},
|
1230 |
-
{
|
1231 |
-
"epoch": 1.5240174672489082,
|
1232 |
-
"grad_norm": 1.03125,
|
1233 |
-
"learning_rate": 7.266727043033386e-06,
|
1234 |
-
"loss": 2.5236,
|
1235 |
-
"step": 175
|
1236 |
-
},
|
1237 |
-
{
|
1238 |
-
"epoch": 1.532751091703057,
|
1239 |
-
"grad_norm": 0.96875,
|
1240 |
-
"learning_rate": 7.234407440147266e-06,
|
1241 |
-
"loss": 2.5656,
|
1242 |
-
"step": 176
|
1243 |
-
},
|
1244 |
-
{
|
1245 |
-
"epoch": 1.5414847161572052,
|
1246 |
-
"grad_norm": 0.98828125,
|
1247 |
-
"learning_rate": 7.201970757788172e-06,
|
1248 |
-
"loss": 2.5682,
|
1249 |
-
"step": 177
|
1250 |
-
},
|
1251 |
-
{
|
1252 |
-
"epoch": 1.5502183406113537,
|
1253 |
-
"grad_norm": 0.96484375,
|
1254 |
-
"learning_rate": 7.169418695587791e-06,
|
1255 |
-
"loss": 2.5356,
|
1256 |
-
"step": 178
|
1257 |
-
},
|
1258 |
-
{
|
1259 |
-
"epoch": 1.5589519650655022,
|
1260 |
-
"grad_norm": 0.96875,
|
1261 |
-
"learning_rate": 7.136752959223527e-06,
|
1262 |
-
"loss": 2.6174,
|
1263 |
-
"step": 179
|
1264 |
-
},
|
1265 |
-
{
|
1266 |
-
"epoch": 1.5676855895196506,
|
1267 |
-
"grad_norm": 0.93359375,
|
1268 |
-
"learning_rate": 7.103975260329136e-06,
|
1269 |
-
"loss": 2.6003,
|
1270 |
-
"step": 180
|
1271 |
-
},
|
1272 |
-
{
|
1273 |
-
"epoch": 1.5764192139737991,
|
1274 |
-
"grad_norm": 0.9140625,
|
1275 |
-
"learning_rate": 7.071087316405037e-06,
|
1276 |
-
"loss": 2.5504,
|
1277 |
-
"step": 181
|
1278 |
-
},
|
1279 |
-
{
|
1280 |
-
"epoch": 1.5851528384279476,
|
1281 |
-
"grad_norm": 0.93359375,
|
1282 |
-
"learning_rate": 7.038090850728312e-06,
|
1283 |
-
"loss": 2.5491,
|
1284 |
-
"step": 182
|
1285 |
-
},
|
1286 |
-
{
|
1287 |
-
"epoch": 1.5938864628820961,
|
1288 |
-
"grad_norm": 0.9296875,
|
1289 |
-
"learning_rate": 7.00498759226242e-06,
|
1290 |
-
"loss": 2.5331,
|
1291 |
-
"step": 183
|
1292 |
-
},
|
1293 |
-
{
|
1294 |
-
"epoch": 1.6026200873362444,
|
1295 |
-
"grad_norm": 0.921875,
|
1296 |
-
"learning_rate": 6.971779275566593e-06,
|
1297 |
-
"loss": 2.537,
|
1298 |
-
"step": 184
|
1299 |
-
},
|
1300 |
-
{
|
1301 |
-
"epoch": 1.611353711790393,
|
1302 |
-
"grad_norm": 0.94140625,
|
1303 |
-
"learning_rate": 6.938467640704953e-06,
|
1304 |
-
"loss": 2.5117,
|
1305 |
-
"step": 185
|
1306 |
-
},
|
1307 |
-
{
|
1308 |
-
"epoch": 1.6200873362445414,
|
1309 |
-
"grad_norm": 0.93359375,
|
1310 |
-
"learning_rate": 6.90505443315533e-06,
|
1311 |
-
"loss": 2.6398,
|
1312 |
-
"step": 186
|
1313 |
-
},
|
1314 |
-
{
|
1315 |
-
"epoch": 1.62882096069869,
|
1316 |
-
"grad_norm": 0.9609375,
|
1317 |
-
"learning_rate": 6.871541403717808e-06,
|
1318 |
-
"loss": 2.5182,
|
1319 |
-
"step": 187
|
1320 |
-
},
|
1321 |
-
{
|
1322 |
-
"epoch": 1.6375545851528384,
|
1323 |
-
"grad_norm": 0.9296875,
|
1324 |
-
"learning_rate": 6.8379303084229765e-06,
|
1325 |
-
"loss": 2.6042,
|
1326 |
-
"step": 188
|
1327 |
-
},
|
1328 |
-
{
|
1329 |
-
"epoch": 1.6462882096069869,
|
1330 |
-
"grad_norm": 0.953125,
|
1331 |
-
"learning_rate": 6.8042229084399325e-06,
|
1332 |
-
"loss": 2.5974,
|
1333 |
-
"step": 189
|
1334 |
-
},
|
1335 |
-
{
|
1336 |
-
"epoch": 1.6550218340611353,
|
1337 |
-
"grad_norm": 0.98828125,
|
1338 |
-
"learning_rate": 6.770420969983982e-06,
|
1339 |
-
"loss": 2.5706,
|
1340 |
-
"step": 190
|
1341 |
-
},
|
1342 |
-
{
|
1343 |
-
"epoch": 1.6637554585152838,
|
1344 |
-
"grad_norm": 1.0,
|
1345 |
-
"learning_rate": 6.736526264224101e-06,
|
1346 |
-
"loss": 2.4622,
|
1347 |
-
"step": 191
|
1348 |
-
},
|
1349 |
-
{
|
1350 |
-
"epoch": 1.6724890829694323,
|
1351 |
-
"grad_norm": 0.9375,
|
1352 |
-
"learning_rate": 6.702540567190132e-06,
|
1353 |
-
"loss": 2.5172,
|
1354 |
-
"step": 192
|
1355 |
-
},
|
1356 |
-
{
|
1357 |
-
"epoch": 1.6812227074235808,
|
1358 |
-
"grad_norm": 0.9453125,
|
1359 |
-
"learning_rate": 6.668465659679714e-06,
|
1360 |
-
"loss": 2.5317,
|
1361 |
-
"step": 193
|
1362 |
-
},
|
1363 |
-
{
|
1364 |
-
"epoch": 1.6899563318777293,
|
1365 |
-
"grad_norm": 1.046875,
|
1366 |
-
"learning_rate": 6.634303327164976e-06,
|
1367 |
-
"loss": 2.5942,
|
1368 |
-
"step": 194
|
1369 |
-
},
|
1370 |
-
{
|
1371 |
-
"epoch": 1.6986899563318776,
|
1372 |
-
"grad_norm": 0.9765625,
|
1373 |
-
"learning_rate": 6.600055359698984e-06,
|
1374 |
-
"loss": 2.5432,
|
1375 |
-
"step": 195
|
1376 |
-
},
|
1377 |
-
{
|
1378 |
-
"epoch": 1.7074235807860263,
|
1379 |
-
"grad_norm": 1.0234375,
|
1380 |
-
"learning_rate": 6.565723551821943e-06,
|
1381 |
-
"loss": 2.532,
|
1382 |
-
"step": 196
|
1383 |
-
},
|
1384 |
-
{
|
1385 |
-
"epoch": 1.7161572052401746,
|
1386 |
-
"grad_norm": 0.9609375,
|
1387 |
-
"learning_rate": 6.531309702467159e-06,
|
1388 |
-
"loss": 2.4832,
|
1389 |
-
"step": 197
|
1390 |
-
},
|
1391 |
-
{
|
1392 |
-
"epoch": 1.7248908296943233,
|
1393 |
-
"grad_norm": 0.9296875,
|
1394 |
-
"learning_rate": 6.496815614866792e-06,
|
1395 |
-
"loss": 2.5488,
|
1396 |
-
"step": 198
|
1397 |
-
},
|
1398 |
-
{
|
1399 |
-
"epoch": 1.7336244541484715,
|
1400 |
-
"grad_norm": 0.9296875,
|
1401 |
-
"learning_rate": 6.462243096457352e-06,
|
1402 |
-
"loss": 2.6082,
|
1403 |
-
"step": 199
|
1404 |
-
},
|
1405 |
-
{
|
1406 |
-
"epoch": 1.74235807860262,
|
1407 |
-
"grad_norm": 0.9609375,
|
1408 |
-
"learning_rate": 6.42759395878501e-06,
|
1409 |
-
"loss": 2.5815,
|
1410 |
-
"step": 200
|
1411 |
-
},
|
1412 |
-
{
|
1413 |
-
"epoch": 1.7510917030567685,
|
1414 |
-
"grad_norm": 0.9609375,
|
1415 |
-
"learning_rate": 6.392870017410665e-06,
|
1416 |
-
"loss": 2.4902,
|
1417 |
-
"step": 201
|
1418 |
-
},
|
1419 |
-
{
|
1420 |
-
"epoch": 1.759825327510917,
|
1421 |
-
"grad_norm": 0.9375,
|
1422 |
-
"learning_rate": 6.358073091814809e-06,
|
1423 |
-
"loss": 2.4882,
|
1424 |
-
"step": 202
|
1425 |
-
},
|
1426 |
-
{
|
1427 |
-
"epoch": 1.7685589519650655,
|
1428 |
-
"grad_norm": 1.0,
|
1429 |
-
"learning_rate": 6.323205005302199e-06,
|
1430 |
-
"loss": 2.5042,
|
1431 |
-
"step": 203
|
1432 |
-
},
|
1433 |
-
{
|
1434 |
-
"epoch": 1.777292576419214,
|
1435 |
-
"grad_norm": 0.953125,
|
1436 |
-
"learning_rate": 6.288267584906308e-06,
|
1437 |
-
"loss": 2.5471,
|
1438 |
-
"step": 204
|
1439 |
-
},
|
1440 |
-
{
|
1441 |
-
"epoch": 1.7860262008733625,
|
1442 |
-
"grad_norm": 0.91796875,
|
1443 |
-
"learning_rate": 6.2532626612936035e-06,
|
1444 |
-
"loss": 2.5491,
|
1445 |
-
"step": 205
|
1446 |
-
},
|
1447 |
-
{
|
1448 |
-
"epoch": 1.7947598253275108,
|
1449 |
-
"grad_norm": 0.93359375,
|
1450 |
-
"learning_rate": 6.21819206866761e-06,
|
1451 |
-
"loss": 2.5086,
|
1452 |
-
"step": 206
|
1453 |
-
},
|
1454 |
-
{
|
1455 |
-
"epoch": 1.8034934497816595,
|
1456 |
-
"grad_norm": 1.1484375,
|
1457 |
-
"learning_rate": 6.18305764467281e-06,
|
1458 |
-
"loss": 2.585,
|
1459 |
-
"step": 207
|
1460 |
-
},
|
1461 |
-
{
|
1462 |
-
"epoch": 1.8122270742358078,
|
1463 |
-
"grad_norm": 0.99609375,
|
1464 |
-
"learning_rate": 6.147861230298349e-06,
|
1465 |
-
"loss": 2.564,
|
1466 |
-
"step": 208
|
1467 |
-
},
|
1468 |
-
{
|
1469 |
-
"epoch": 1.8209606986899565,
|
1470 |
-
"grad_norm": 1.0859375,
|
1471 |
-
"learning_rate": 6.112604669781572e-06,
|
1472 |
-
"loss": 2.5534,
|
1473 |
-
"step": 209
|
1474 |
-
},
|
1475 |
-
{
|
1476 |
-
"epoch": 1.8296943231441047,
|
1477 |
-
"grad_norm": 1.0234375,
|
1478 |
-
"learning_rate": 6.077289810511389e-06,
|
1479 |
-
"loss": 2.5989,
|
1480 |
-
"step": 210
|
1481 |
-
},
|
1482 |
-
{
|
1483 |
-
"epoch": 1.8384279475982532,
|
1484 |
-
"grad_norm": 1.0078125,
|
1485 |
-
"learning_rate": 6.041918502931473e-06,
|
1486 |
-
"loss": 2.5781,
|
1487 |
-
"step": 211
|
1488 |
-
},
|
1489 |
-
{
|
1490 |
-
"epoch": 1.8471615720524017,
|
1491 |
-
"grad_norm": 1.1171875,
|
1492 |
-
"learning_rate": 6.006492600443301e-06,
|
1493 |
-
"loss": 2.4495,
|
1494 |
-
"step": 212
|
1495 |
-
},
|
1496 |
-
{
|
1497 |
-
"epoch": 1.8558951965065502,
|
1498 |
-
"grad_norm": 1.0,
|
1499 |
-
"learning_rate": 5.971013959309038e-06,
|
1500 |
-
"loss": 2.4965,
|
1501 |
-
"step": 213
|
1502 |
-
},
|
1503 |
-
{
|
1504 |
-
"epoch": 1.8646288209606987,
|
1505 |
-
"grad_norm": 0.96875,
|
1506 |
-
"learning_rate": 5.935484438554273e-06,
|
1507 |
-
"loss": 2.5466,
|
1508 |
-
"step": 214
|
1509 |
-
},
|
1510 |
-
{
|
1511 |
-
"epoch": 1.8733624454148472,
|
1512 |
-
"grad_norm": 0.94140625,
|
1513 |
-
"learning_rate": 5.8999058998706046e-06,
|
1514 |
-
"loss": 2.447,
|
1515 |
-
"step": 215
|
1516 |
-
},
|
1517 |
-
{
|
1518 |
-
"epoch": 1.8820960698689957,
|
1519 |
-
"grad_norm": 0.98828125,
|
1520 |
-
"learning_rate": 5.8642802075181e-06,
|
1521 |
-
"loss": 2.5911,
|
1522 |
-
"step": 216
|
1523 |
-
},
|
1524 |
-
{
|
1525 |
-
"epoch": 1.890829694323144,
|
1526 |
-
"grad_norm": 1.1015625,
|
1527 |
-
"learning_rate": 5.828609228227603e-06,
|
1528 |
-
"loss": 2.5723,
|
1529 |
-
"step": 217
|
1530 |
-
},
|
1531 |
-
{
|
1532 |
-
"epoch": 1.8995633187772927,
|
1533 |
-
"grad_norm": 1.015625,
|
1534 |
-
"learning_rate": 5.7928948311029175e-06,
|
1535 |
-
"loss": 2.6029,
|
1536 |
-
"step": 218
|
1537 |
-
},
|
1538 |
-
{
|
1539 |
-
"epoch": 1.908296943231441,
|
1540 |
-
"grad_norm": 1.0078125,
|
1541 |
-
"learning_rate": 5.757138887522884e-06,
|
1542 |
-
"loss": 2.5432,
|
1543 |
-
"step": 219
|
1544 |
-
},
|
1545 |
-
{
|
1546 |
-
"epoch": 1.9170305676855897,
|
1547 |
-
"grad_norm": 0.94140625,
|
1548 |
-
"learning_rate": 5.721343271043305e-06,
|
1549 |
-
"loss": 2.5273,
|
1550 |
-
"step": 220
|
1551 |
-
},
|
1552 |
-
{
|
1553 |
-
"epoch": 1.925764192139738,
|
1554 |
-
"grad_norm": 0.93359375,
|
1555 |
-
"learning_rate": 5.685509857298781e-06,
|
1556 |
-
"loss": 2.5822,
|
1557 |
-
"step": 221
|
1558 |
-
},
|
1559 |
-
{
|
1560 |
-
"epoch": 1.9344978165938864,
|
1561 |
-
"grad_norm": 0.97265625,
|
1562 |
-
"learning_rate": 5.649640523904438e-06,
|
1563 |
-
"loss": 2.4545,
|
1564 |
-
"step": 222
|
1565 |
-
},
|
1566 |
-
{
|
1567 |
-
"epoch": 1.943231441048035,
|
1568 |
-
"grad_norm": 0.95703125,
|
1569 |
-
"learning_rate": 5.613737150357528e-06,
|
1570 |
-
"loss": 2.6138,
|
1571 |
-
"step": 223
|
1572 |
-
},
|
1573 |
-
{
|
1574 |
-
"epoch": 1.9519650655021834,
|
1575 |
-
"grad_norm": 0.984375,
|
1576 |
-
"learning_rate": 5.577801617938956e-06,
|
1577 |
-
"loss": 2.5428,
|
1578 |
-
"step": 224
|
1579 |
-
},
|
1580 |
-
{
|
1581 |
-
"epoch": 1.960698689956332,
|
1582 |
-
"grad_norm": 0.96875,
|
1583 |
-
"learning_rate": 5.541835809614704e-06,
|
1584 |
-
"loss": 2.4883,
|
1585 |
-
"step": 225
|
1586 |
-
},
|
1587 |
-
{
|
1588 |
-
"epoch": 1.9694323144104804,
|
1589 |
-
"grad_norm": 0.97265625,
|
1590 |
-
"learning_rate": 5.505841609937162e-06,
|
1591 |
-
"loss": 2.5128,
|
1592 |
-
"step": 226
|
1593 |
-
},
|
1594 |
-
{
|
1595 |
-
"epoch": 1.9781659388646289,
|
1596 |
-
"grad_norm": 0.9375,
|
1597 |
-
"learning_rate": 5.469820904946383e-06,
|
1598 |
-
"loss": 2.5452,
|
1599 |
-
"step": 227
|
1600 |
-
},
|
1601 |
-
{
|
1602 |
-
"epoch": 1.9868995633187772,
|
1603 |
-
"grad_norm": 0.98828125,
|
1604 |
-
"learning_rate": 5.43377558207126e-06,
|
1605 |
-
"loss": 2.5695,
|
1606 |
-
"step": 228
|
1607 |
-
},
|
1608 |
-
{
|
1609 |
-
"epoch": 1.9956331877729259,
|
1610 |
-
"grad_norm": 0.9765625,
|
1611 |
-
"learning_rate": 5.397707530030621e-06,
|
1612 |
-
"loss": 2.4972,
|
1613 |
-
"step": 229
|
1614 |
-
},
|
1615 |
-
{
|
1616 |
-
"epoch": 2.0,
|
1617 |
-
"grad_norm": 2.140625,
|
1618 |
-
"learning_rate": 5.36161863873427e-06,
|
1619 |
-
"loss": 2.5345,
|
1620 |
-
"step": 230
|
1621 |
-
},
|
1622 |
-
{
|
1623 |
-
"epoch": 2.0087336244541483,
|
1624 |
-
"grad_norm": 0.96484375,
|
1625 |
-
"learning_rate": 5.325510799183953e-06,
|
1626 |
-
"loss": 2.5283,
|
1627 |
-
"step": 231
|
1628 |
-
},
|
1629 |
-
{
|
1630 |
-
"epoch": 2.017467248908297,
|
1631 |
-
"grad_norm": 0.9296875,
|
1632 |
-
"learning_rate": 5.289385903374273e-06,
|
1633 |
-
"loss": 2.5429,
|
1634 |
-
"step": 232
|
1635 |
-
},
|
1636 |
-
{
|
1637 |
-
"epoch": 2.0262008733624453,
|
1638 |
-
"grad_norm": 0.95703125,
|
1639 |
-
"learning_rate": 5.253245844193564e-06,
|
1640 |
-
"loss": 2.5203,
|
1641 |
-
"step": 233
|
1642 |
-
},
|
1643 |
-
{
|
1644 |
-
"epoch": 2.034934497816594,
|
1645 |
-
"grad_norm": 0.94921875,
|
1646 |
-
"learning_rate": 5.217092515324687e-06,
|
1647 |
-
"loss": 2.5659,
|
1648 |
-
"step": 234
|
1649 |
-
},
|
1650 |
-
{
|
1651 |
-
"epoch": 2.0436681222707422,
|
1652 |
-
"grad_norm": 0.95703125,
|
1653 |
-
"learning_rate": 5.180927811145818e-06,
|
1654 |
-
"loss": 2.5941,
|
1655 |
-
"step": 235
|
1656 |
-
},
|
1657 |
-
{
|
1658 |
-
"epoch": 2.052401746724891,
|
1659 |
-
"grad_norm": 0.94921875,
|
1660 |
-
"learning_rate": 5.144753626631179e-06,
|
1661 |
-
"loss": 2.6062,
|
1662 |
-
"step": 236
|
1663 |
-
},
|
1664 |
-
{
|
1665 |
-
"epoch": 2.061135371179039,
|
1666 |
-
"grad_norm": 0.93359375,
|
1667 |
-
"learning_rate": 5.108571857251754e-06,
|
1668 |
-
"loss": 2.5176,
|
1669 |
-
"step": 237
|
1670 |
-
},
|
1671 |
-
{
|
1672 |
-
"epoch": 2.069868995633188,
|
1673 |
-
"grad_norm": 0.95703125,
|
1674 |
-
"learning_rate": 5.072384398875953e-06,
|
1675 |
-
"loss": 2.5255,
|
1676 |
-
"step": 238
|
1677 |
-
},
|
1678 |
-
{
|
1679 |
-
"epoch": 2.078602620087336,
|
1680 |
-
"grad_norm": 0.9375,
|
1681 |
-
"learning_rate": 5.036193147670286e-06,
|
1682 |
-
"loss": 2.6136,
|
1683 |
-
"step": 239
|
1684 |
-
},
|
1685 |
-
{
|
1686 |
-
"epoch": 2.087336244541485,
|
1687 |
-
"grad_norm": 0.953125,
|
1688 |
-
"learning_rate": 5e-06,
|
1689 |
-
"loss": 2.5102,
|
1690 |
-
"step": 240
|
1691 |
-
},
|
1692 |
-
{
|
1693 |
-
"epoch": 2.096069868995633,
|
1694 |
-
"grad_norm": 0.9375,
|
1695 |
-
"learning_rate": 4.963806852329715e-06,
|
1696 |
-
"loss": 2.5428,
|
1697 |
-
"step": 241
|
1698 |
-
},
|
1699 |
-
{
|
1700 |
-
"epoch": 2.1048034934497815,
|
1701 |
-
"grad_norm": 0.94140625,
|
1702 |
-
"learning_rate": 4.927615601124049e-06,
|
1703 |
-
"loss": 2.6019,
|
1704 |
-
"step": 242
|
1705 |
-
},
|
1706 |
-
{
|
1707 |
-
"epoch": 2.11353711790393,
|
1708 |
-
"grad_norm": 0.93359375,
|
1709 |
-
"learning_rate": 4.891428142748247e-06,
|
1710 |
-
"loss": 2.5244,
|
1711 |
-
"step": 243
|
1712 |
-
},
|
1713 |
-
{
|
1714 |
-
"epoch": 2.1222707423580784,
|
1715 |
-
"grad_norm": 0.99609375,
|
1716 |
-
"learning_rate": 4.855246373368822e-06,
|
1717 |
-
"loss": 2.4555,
|
1718 |
-
"step": 244
|
1719 |
-
},
|
1720 |
-
{
|
1721 |
-
"epoch": 2.131004366812227,
|
1722 |
-
"grad_norm": 0.95703125,
|
1723 |
-
"learning_rate": 4.819072188854183e-06,
|
1724 |
-
"loss": 2.6127,
|
1725 |
-
"step": 245
|
1726 |
-
},
|
1727 |
-
{
|
1728 |
-
"epoch": 2.1397379912663754,
|
1729 |
-
"grad_norm": 0.9765625,
|
1730 |
-
"learning_rate": 4.782907484675314e-06,
|
1731 |
-
"loss": 2.4867,
|
1732 |
-
"step": 246
|
1733 |
-
},
|
1734 |
-
{
|
1735 |
-
"epoch": 2.148471615720524,
|
1736 |
-
"grad_norm": 0.95703125,
|
1737 |
-
"learning_rate": 4.746754155806437e-06,
|
1738 |
-
"loss": 2.4869,
|
1739 |
-
"step": 247
|
1740 |
-
},
|
1741 |
-
{
|
1742 |
-
"epoch": 2.1572052401746724,
|
1743 |
-
"grad_norm": 0.92578125,
|
1744 |
-
"learning_rate": 4.710614096625727e-06,
|
1745 |
-
"loss": 2.5848,
|
1746 |
-
"step": 248
|
1747 |
-
},
|
1748 |
-
{
|
1749 |
-
"epoch": 2.165938864628821,
|
1750 |
-
"grad_norm": 0.96484375,
|
1751 |
-
"learning_rate": 4.674489200816051e-06,
|
1752 |
-
"loss": 2.5852,
|
1753 |
-
"step": 249
|
1754 |
-
},
|
1755 |
-
{
|
1756 |
-
"epoch": 2.1746724890829694,
|
1757 |
-
"grad_norm": 0.9375,
|
1758 |
-
"learning_rate": 4.638381361265731e-06,
|
1759 |
-
"loss": 2.5593,
|
1760 |
-
"step": 250
|
1761 |
-
},
|
1762 |
-
{
|
1763 |
-
"epoch": 2.183406113537118,
|
1764 |
-
"grad_norm": 0.94921875,
|
1765 |
-
"learning_rate": 4.602292469969381e-06,
|
1766 |
-
"loss": 2.5104,
|
1767 |
-
"step": 251
|
1768 |
-
},
|
1769 |
-
{
|
1770 |
-
"epoch": 2.1921397379912664,
|
1771 |
-
"grad_norm": 0.94140625,
|
1772 |
-
"learning_rate": 4.5662244179287415e-06,
|
1773 |
-
"loss": 2.5329,
|
1774 |
-
"step": 252
|
1775 |
-
},
|
1776 |
-
{
|
1777 |
-
"epoch": 2.2008733624454146,
|
1778 |
-
"grad_norm": 0.9765625,
|
1779 |
-
"learning_rate": 4.5301790950536175e-06,
|
1780 |
-
"loss": 2.4718,
|
1781 |
-
"step": 253
|
1782 |
-
},
|
1783 |
-
{
|
1784 |
-
"epoch": 2.2096069868995634,
|
1785 |
-
"grad_norm": 0.96875,
|
1786 |
-
"learning_rate": 4.49415839006284e-06,
|
1787 |
-
"loss": 2.6102,
|
1788 |
-
"step": 254
|
1789 |
-
},
|
1790 |
-
{
|
1791 |
-
"epoch": 2.2183406113537116,
|
1792 |
-
"grad_norm": 0.96484375,
|
1793 |
-
"learning_rate": 4.458164190385297e-06,
|
1794 |
-
"loss": 2.486,
|
1795 |
-
"step": 255
|
1796 |
-
},
|
1797 |
-
{
|
1798 |
-
"epoch": 2.2270742358078603,
|
1799 |
-
"grad_norm": 0.94921875,
|
1800 |
-
"learning_rate": 4.4221983820610466e-06,
|
1801 |
-
"loss": 2.5996,
|
1802 |
-
"step": 256
|
1803 |
-
},
|
1804 |
-
{
|
1805 |
-
"epoch": 2.2358078602620086,
|
1806 |
-
"grad_norm": 0.921875,
|
1807 |
-
"learning_rate": 4.386262849642474e-06,
|
1808 |
-
"loss": 2.4844,
|
1809 |
-
"step": 257
|
1810 |
-
},
|
1811 |
-
{
|
1812 |
-
"epoch": 2.2445414847161573,
|
1813 |
-
"grad_norm": 1.015625,
|
1814 |
-
"learning_rate": 4.350359476095563e-06,
|
1815 |
-
"loss": 2.5879,
|
1816 |
-
"step": 258
|
1817 |
-
},
|
1818 |
-
{
|
1819 |
-
"epoch": 2.2532751091703056,
|
1820 |
-
"grad_norm": 0.98046875,
|
1821 |
-
"learning_rate": 4.31449014270122e-06,
|
1822 |
-
"loss": 2.5687,
|
1823 |
-
"step": 259
|
1824 |
-
},
|
1825 |
-
{
|
1826 |
-
"epoch": 2.2620087336244543,
|
1827 |
-
"grad_norm": 0.953125,
|
1828 |
-
"learning_rate": 4.278656728956697e-06,
|
1829 |
-
"loss": 2.5688,
|
1830 |
-
"step": 260
|
1831 |
-
},
|
1832 |
-
{
|
1833 |
-
"epoch": 2.2707423580786026,
|
1834 |
-
"grad_norm": 0.953125,
|
1835 |
-
"learning_rate": 4.2428611124771184e-06,
|
1836 |
-
"loss": 2.5951,
|
1837 |
-
"step": 261
|
1838 |
-
},
|
1839 |
-
{
|
1840 |
-
"epoch": 2.279475982532751,
|
1841 |
-
"grad_norm": 0.9296875,
|
1842 |
-
"learning_rate": 4.207105168897083e-06,
|
1843 |
-
"loss": 2.5171,
|
1844 |
-
"step": 262
|
1845 |
-
},
|
1846 |
-
{
|
1847 |
-
"epoch": 2.2882096069868996,
|
1848 |
-
"grad_norm": 0.9296875,
|
1849 |
-
"learning_rate": 4.171390771772399e-06,
|
1850 |
-
"loss": 2.5262,
|
1851 |
-
"step": 263
|
1852 |
-
},
|
1853 |
-
{
|
1854 |
-
"epoch": 2.2969432314410483,
|
1855 |
-
"grad_norm": 0.96875,
|
1856 |
-
"learning_rate": 4.135719792481901e-06,
|
1857 |
-
"loss": 2.5722,
|
1858 |
-
"step": 264
|
1859 |
-
},
|
1860 |
-
{
|
1861 |
-
"epoch": 2.3056768558951966,
|
1862 |
-
"grad_norm": 0.90625,
|
1863 |
-
"learning_rate": 4.100094100129396e-06,
|
1864 |
-
"loss": 2.5025,
|
1865 |
-
"step": 265
|
1866 |
-
},
|
1867 |
-
{
|
1868 |
-
"epoch": 2.314410480349345,
|
1869 |
-
"grad_norm": 0.94140625,
|
1870 |
-
"learning_rate": 4.06451556144573e-06,
|
1871 |
-
"loss": 2.5283,
|
1872 |
-
"step": 266
|
1873 |
-
},
|
1874 |
-
{
|
1875 |
-
"epoch": 2.3231441048034935,
|
1876 |
-
"grad_norm": 0.94921875,
|
1877 |
-
"learning_rate": 4.028986040690963e-06,
|
1878 |
-
"loss": 2.5674,
|
1879 |
-
"step": 267
|
1880 |
-
},
|
1881 |
-
{
|
1882 |
-
"epoch": 2.331877729257642,
|
1883 |
-
"grad_norm": 0.97265625,
|
1884 |
-
"learning_rate": 3.993507399556699e-06,
|
1885 |
-
"loss": 2.5345,
|
1886 |
-
"step": 268
|
1887 |
-
},
|
1888 |
-
{
|
1889 |
-
"epoch": 2.3406113537117905,
|
1890 |
-
"grad_norm": 0.96875,
|
1891 |
-
"learning_rate": 3.958081497068528e-06,
|
1892 |
-
"loss": 2.4415,
|
1893 |
-
"step": 269
|
1894 |
-
},
|
1895 |
-
{
|
1896 |
-
"epoch": 2.349344978165939,
|
1897 |
-
"grad_norm": 0.9375,
|
1898 |
-
"learning_rate": 3.922710189488612e-06,
|
1899 |
-
"loss": 2.5205,
|
1900 |
-
"step": 270
|
1901 |
-
},
|
1902 |
-
{
|
1903 |
-
"epoch": 2.3580786026200875,
|
1904 |
-
"grad_norm": 0.96484375,
|
1905 |
-
"learning_rate": 3.887395330218429e-06,
|
1906 |
-
"loss": 2.5556,
|
1907 |
-
"step": 271
|
1908 |
-
},
|
1909 |
-
{
|
1910 |
-
"epoch": 2.3668122270742358,
|
1911 |
-
"grad_norm": 0.96875,
|
1912 |
-
"learning_rate": 3.852138769701652e-06,
|
1913 |
-
"loss": 2.5574,
|
1914 |
-
"step": 272
|
1915 |
-
},
|
1916 |
-
{
|
1917 |
-
"epoch": 2.3755458515283845,
|
1918 |
-
"grad_norm": 0.95703125,
|
1919 |
-
"learning_rate": 3.816942355327191e-06,
|
1920 |
-
"loss": 2.5229,
|
1921 |
-
"step": 273
|
1922 |
-
},
|
1923 |
-
{
|
1924 |
-
"epoch": 2.3842794759825328,
|
1925 |
-
"grad_norm": 0.93359375,
|
1926 |
-
"learning_rate": 3.7818079313323906e-06,
|
1927 |
-
"loss": 2.6236,
|
1928 |
-
"step": 274
|
1929 |
-
},
|
1930 |
-
{
|
1931 |
-
"epoch": 2.393013100436681,
|
1932 |
-
"grad_norm": 0.96484375,
|
1933 |
-
"learning_rate": 3.7467373387063973e-06,
|
1934 |
-
"loss": 2.4755,
|
1935 |
-
"step": 275
|
1936 |
-
},
|
1937 |
-
{
|
1938 |
-
"epoch": 2.4017467248908297,
|
1939 |
-
"grad_norm": 1.0078125,
|
1940 |
-
"learning_rate": 3.7117324150936936e-06,
|
1941 |
-
"loss": 2.6555,
|
1942 |
-
"step": 276
|
1943 |
-
},
|
1944 |
-
{
|
1945 |
-
"epoch": 2.410480349344978,
|
1946 |
-
"grad_norm": 0.9453125,
|
1947 |
-
"learning_rate": 3.6767949946978026e-06,
|
1948 |
-
"loss": 2.552,
|
1949 |
-
"step": 277
|
1950 |
-
},
|
1951 |
-
{
|
1952 |
-
"epoch": 2.4192139737991267,
|
1953 |
-
"grad_norm": 0.96484375,
|
1954 |
-
"learning_rate": 3.641926908185193e-06,
|
1955 |
-
"loss": 2.5126,
|
1956 |
-
"step": 278
|
1957 |
-
},
|
1958 |
-
{
|
1959 |
-
"epoch": 2.427947598253275,
|
1960 |
-
"grad_norm": 0.98046875,
|
1961 |
-
"learning_rate": 3.607129982589337e-06,
|
1962 |
-
"loss": 2.4944,
|
1963 |
-
"step": 279
|
1964 |
-
},
|
1965 |
-
{
|
1966 |
-
"epoch": 2.4366812227074237,
|
1967 |
-
"grad_norm": 0.9921875,
|
1968 |
-
"learning_rate": 3.5724060412149898e-06,
|
1969 |
-
"loss": 2.6018,
|
1970 |
-
"step": 280
|
1971 |
-
},
|
1972 |
-
{
|
1973 |
-
"epoch": 2.445414847161572,
|
1974 |
-
"grad_norm": 1.03125,
|
1975 |
-
"learning_rate": 3.5377569035426494e-06,
|
1976 |
-
"loss": 2.4682,
|
1977 |
-
"step": 281
|
1978 |
-
},
|
1979 |
-
{
|
1980 |
-
"epoch": 2.4541484716157207,
|
1981 |
-
"grad_norm": 0.9609375,
|
1982 |
-
"learning_rate": 3.5031843851332105e-06,
|
1983 |
-
"loss": 2.546,
|
1984 |
-
"step": 282
|
1985 |
-
},
|
1986 |
-
{
|
1987 |
-
"epoch": 2.462882096069869,
|
1988 |
-
"grad_norm": 0.92578125,
|
1989 |
-
"learning_rate": 3.468690297532843e-06,
|
1990 |
-
"loss": 2.5658,
|
1991 |
-
"step": 283
|
1992 |
-
},
|
1993 |
-
{
|
1994 |
-
"epoch": 2.4716157205240172,
|
1995 |
-
"grad_norm": 0.97265625,
|
1996 |
-
"learning_rate": 3.434276448178059e-06,
|
1997 |
-
"loss": 2.5172,
|
1998 |
-
"step": 284
|
1999 |
-
},
|
2000 |
-
{
|
2001 |
-
"epoch": 2.480349344978166,
|
2002 |
-
"grad_norm": 0.91796875,
|
2003 |
-
"learning_rate": 3.3999446403010156e-06,
|
2004 |
-
"loss": 2.4802,
|
2005 |
-
"step": 285
|
2006 |
-
},
|
2007 |
-
{
|
2008 |
-
"epoch": 2.489082969432314,
|
2009 |
-
"grad_norm": 0.95703125,
|
2010 |
-
"learning_rate": 3.3656966728350254e-06,
|
2011 |
-
"loss": 2.4931,
|
2012 |
-
"step": 286
|
2013 |
-
},
|
2014 |
-
{
|
2015 |
-
"epoch": 2.497816593886463,
|
2016 |
-
"grad_norm": 0.9140625,
|
2017 |
-
"learning_rate": 3.331534340320287e-06,
|
2018 |
-
"loss": 2.5267,
|
2019 |
-
"step": 287
|
2020 |
-
},
|
2021 |
-
{
|
2022 |
-
"epoch": 2.506550218340611,
|
2023 |
-
"grad_norm": 1.0546875,
|
2024 |
-
"learning_rate": 3.29745943280987e-06,
|
2025 |
-
"loss": 2.5716,
|
2026 |
-
"step": 288
|
2027 |
-
},
|
2028 |
-
{
|
2029 |
-
"epoch": 2.51528384279476,
|
2030 |
-
"grad_norm": 0.9765625,
|
2031 |
-
"learning_rate": 3.2634737357758994e-06,
|
2032 |
-
"loss": 2.5257,
|
2033 |
-
"step": 289
|
2034 |
-
},
|
2035 |
-
{
|
2036 |
-
"epoch": 2.524017467248908,
|
2037 |
-
"grad_norm": 0.96484375,
|
2038 |
-
"learning_rate": 3.2295790300160203e-06,
|
2039 |
-
"loss": 2.5126,
|
2040 |
-
"step": 290
|
2041 |
-
},
|
2042 |
-
{
|
2043 |
-
"epoch": 2.532751091703057,
|
2044 |
-
"grad_norm": 0.984375,
|
2045 |
-
"learning_rate": 3.1957770915600696e-06,
|
2046 |
-
"loss": 2.5055,
|
2047 |
-
"step": 291
|
2048 |
-
},
|
2049 |
-
{
|
2050 |
-
"epoch": 2.541484716157205,
|
2051 |
-
"grad_norm": 0.96875,
|
2052 |
-
"learning_rate": 3.1620696915770243e-06,
|
2053 |
-
"loss": 2.5754,
|
2054 |
-
"step": 292
|
2055 |
-
},
|
2056 |
-
{
|
2057 |
-
"epoch": 2.5502183406113534,
|
2058 |
-
"grad_norm": 1.0234375,
|
2059 |
-
"learning_rate": 3.1284585962821957e-06,
|
2060 |
-
"loss": 2.4949,
|
2061 |
-
"step": 293
|
2062 |
-
},
|
2063 |
-
{
|
2064 |
-
"epoch": 2.558951965065502,
|
2065 |
-
"grad_norm": 0.9375,
|
2066 |
-
"learning_rate": 3.0949455668446715e-06,
|
2067 |
-
"loss": 2.5099,
|
2068 |
-
"step": 294
|
2069 |
-
},
|
2070 |
-
{
|
2071 |
-
"epoch": 2.567685589519651,
|
2072 |
-
"grad_norm": 0.9375,
|
2073 |
-
"learning_rate": 3.0615323592950495e-06,
|
2074 |
-
"loss": 2.478,
|
2075 |
-
"step": 295
|
2076 |
-
},
|
2077 |
-
{
|
2078 |
-
"epoch": 2.576419213973799,
|
2079 |
-
"grad_norm": 0.9609375,
|
2080 |
-
"learning_rate": 3.0282207244334084e-06,
|
2081 |
-
"loss": 2.5659,
|
2082 |
-
"step": 296
|
2083 |
-
},
|
2084 |
-
{
|
2085 |
-
"epoch": 2.5851528384279474,
|
2086 |
-
"grad_norm": 1.0546875,
|
2087 |
-
"learning_rate": 2.995012407737581e-06,
|
2088 |
-
"loss": 2.5595,
|
2089 |
-
"step": 297
|
2090 |
-
},
|
2091 |
-
{
|
2092 |
-
"epoch": 2.593886462882096,
|
2093 |
-
"grad_norm": 0.94140625,
|
2094 |
-
"learning_rate": 2.9619091492716896e-06,
|
2095 |
-
"loss": 2.5154,
|
2096 |
-
"step": 298
|
2097 |
-
},
|
2098 |
-
{
|
2099 |
-
"epoch": 2.6026200873362444,
|
2100 |
-
"grad_norm": 1.03125,
|
2101 |
-
"learning_rate": 2.9289126835949657e-06,
|
2102 |
-
"loss": 2.645,
|
2103 |
-
"step": 299
|
2104 |
-
},
|
2105 |
-
{
|
2106 |
-
"epoch": 2.611353711790393,
|
2107 |
-
"grad_norm": 1.0390625,
|
2108 |
-
"learning_rate": 2.896024739670866e-06,
|
2109 |
-
"loss": 2.5351,
|
2110 |
-
"step": 300
|
2111 |
-
},
|
2112 |
-
{
|
2113 |
-
"epoch": 2.6200873362445414,
|
2114 |
-
"grad_norm": 0.9375,
|
2115 |
-
"learning_rate": 2.8632470407764746e-06,
|
2116 |
-
"loss": 2.6008,
|
2117 |
-
"step": 301
|
2118 |
-
},
|
2119 |
-
{
|
2120 |
-
"epoch": 2.62882096069869,
|
2121 |
-
"grad_norm": 0.94921875,
|
2122 |
-
"learning_rate": 2.83058130441221e-06,
|
2123 |
-
"loss": 2.5716,
|
2124 |
-
"step": 302
|
2125 |
-
},
|
2126 |
-
{
|
2127 |
-
"epoch": 2.6375545851528384,
|
2128 |
-
"grad_norm": 0.9765625,
|
2129 |
-
"learning_rate": 2.7980292422118282e-06,
|
2130 |
-
"loss": 2.4846,
|
2131 |
-
"step": 303
|
2132 |
-
},
|
2133 |
-
{
|
2134 |
-
"epoch": 2.646288209606987,
|
2135 |
-
"grad_norm": 0.94921875,
|
2136 |
-
"learning_rate": 2.7655925598527373e-06,
|
2137 |
-
"loss": 2.5733,
|
2138 |
-
"step": 304
|
2139 |
-
},
|
2140 |
-
{
|
2141 |
-
"epoch": 2.6550218340611353,
|
2142 |
-
"grad_norm": 0.9921875,
|
2143 |
-
"learning_rate": 2.733272956966615e-06,
|
2144 |
-
"loss": 2.5963,
|
2145 |
-
"step": 305
|
2146 |
-
},
|
2147 |
-
{
|
2148 |
-
"epoch": 2.6637554585152836,
|
2149 |
-
"grad_norm": 0.93359375,
|
2150 |
-
"learning_rate": 2.7010721270503625e-06,
|
2151 |
-
"loss": 2.4954,
|
2152 |
-
"step": 306
|
2153 |
-
},
|
2154 |
-
{
|
2155 |
-
"epoch": 2.6724890829694323,
|
2156 |
-
"grad_norm": 0.99609375,
|
2157 |
-
"learning_rate": 2.6689917573773615e-06,
|
2158 |
-
"loss": 2.4911,
|
2159 |
-
"step": 307
|
2160 |
-
},
|
2161 |
-
{
|
2162 |
-
"epoch": 2.681222707423581,
|
2163 |
-
"grad_norm": 0.95703125,
|
2164 |
-
"learning_rate": 2.6370335289090654e-06,
|
2165 |
-
"loss": 2.549,
|
2166 |
-
"step": 308
|
2167 |
-
},
|
2168 |
-
{
|
2169 |
-
"epoch": 2.6899563318777293,
|
2170 |
-
"grad_norm": 0.94921875,
|
2171 |
-
"learning_rate": 2.605199116206912e-06,
|
2172 |
-
"loss": 2.5247,
|
2173 |
-
"step": 309
|
2174 |
-
},
|
2175 |
-
{
|
2176 |
-
"epoch": 2.6986899563318776,
|
2177 |
-
"grad_norm": 0.921875,
|
2178 |
-
"learning_rate": 2.573490187344596e-06,
|
2179 |
-
"loss": 2.4895,
|
2180 |
-
"step": 310
|
2181 |
-
},
|
2182 |
-
{
|
2183 |
-
"epoch": 2.7074235807860263,
|
2184 |
-
"grad_norm": 0.96484375,
|
2185 |
-
"learning_rate": 2.5419084038206422e-06,
|
2186 |
-
"loss": 2.567,
|
2187 |
-
"step": 311
|
2188 |
-
},
|
2189 |
-
{
|
2190 |
-
"epoch": 2.7161572052401746,
|
2191 |
-
"grad_norm": 1.046875,
|
2192 |
-
"learning_rate": 2.510455420471369e-06,
|
2193 |
-
"loss": 2.5381,
|
2194 |
-
"step": 312
|
2195 |
-
},
|
2196 |
-
{
|
2197 |
-
"epoch": 2.7248908296943233,
|
2198 |
-
"grad_norm": 0.96875,
|
2199 |
-
"learning_rate": 2.4791328853841577e-06,
|
2200 |
-
"loss": 2.5808,
|
2201 |
-
"step": 313
|
2202 |
-
},
|
2203 |
-
{
|
2204 |
-
"epoch": 2.7336244541484715,
|
2205 |
-
"grad_norm": 0.953125,
|
2206 |
-
"learning_rate": 2.447942439811108e-06,
|
2207 |
-
"loss": 2.4982,
|
2208 |
-
"step": 314
|
2209 |
-
},
|
2210 |
-
{
|
2211 |
-
"epoch": 2.74235807860262,
|
2212 |
-
"grad_norm": 1.046875,
|
2213 |
-
"learning_rate": 2.416885718083035e-06,
|
2214 |
-
"loss": 2.5771,
|
2215 |
-
"step": 315
|
2216 |
-
},
|
2217 |
-
{
|
2218 |
-
"epoch": 2.7510917030567685,
|
2219 |
-
"grad_norm": 0.984375,
|
2220 |
-
"learning_rate": 2.3859643475238264e-06,
|
2221 |
-
"loss": 2.5165,
|
2222 |
-
"step": 316
|
2223 |
-
},
|
2224 |
-
{
|
2225 |
-
"epoch": 2.7598253275109172,
|
2226 |
-
"grad_norm": 1.0,
|
2227 |
-
"learning_rate": 2.3551799483651894e-06,
|
2228 |
-
"loss": 2.4792,
|
2229 |
-
"step": 317
|
2230 |
-
},
|
2231 |
-
{
|
2232 |
-
"epoch": 2.7685589519650655,
|
2233 |
-
"grad_norm": 0.97265625,
|
2234 |
-
"learning_rate": 2.3245341336617326e-06,
|
2235 |
-
"loss": 2.513,
|
2236 |
-
"step": 318
|
2237 |
-
},
|
2238 |
-
{
|
2239 |
-
"epoch": 2.777292576419214,
|
2240 |
-
"grad_norm": 0.9375,
|
2241 |
-
"learning_rate": 2.294028509206461e-06,
|
2242 |
-
"loss": 2.5532,
|
2243 |
-
"step": 319
|
2244 |
-
},
|
2245 |
-
{
|
2246 |
-
"epoch": 2.7860262008733625,
|
2247 |
-
"grad_norm": 0.96484375,
|
2248 |
-
"learning_rate": 2.2636646734466296e-06,
|
2249 |
-
"loss": 2.4953,
|
2250 |
-
"step": 320
|
2251 |
-
},
|
2252 |
-
{
|
2253 |
-
"epoch": 2.7947598253275108,
|
2254 |
-
"grad_norm": 0.984375,
|
2255 |
-
"learning_rate": 2.2334442173999794e-06,
|
2256 |
-
"loss": 2.476,
|
2257 |
-
"step": 321
|
2258 |
-
},
|
2259 |
-
{
|
2260 |
-
"epoch": 2.8034934497816595,
|
2261 |
-
"grad_norm": 0.93359375,
|
2262 |
-
"learning_rate": 2.2033687245713847e-06,
|
2263 |
-
"loss": 2.5595,
|
2264 |
-
"step": 322
|
2265 |
-
},
|
2266 |
-
{
|
2267 |
-
"epoch": 2.8122270742358078,
|
2268 |
-
"grad_norm": 0.95703125,
|
2269 |
-
"learning_rate": 2.17343977086987e-06,
|
2270 |
-
"loss": 2.5262,
|
2271 |
-
"step": 323
|
2272 |
-
},
|
2273 |
-
{
|
2274 |
-
"epoch": 2.8209606986899565,
|
2275 |
-
"grad_norm": 0.9765625,
|
2276 |
-
"learning_rate": 2.1436589245260375e-06,
|
2277 |
-
"loss": 2.5172,
|
2278 |
-
"step": 324
|
2279 |
-
},
|
2280 |
-
{
|
2281 |
-
"epoch": 2.8296943231441047,
|
2282 |
-
"grad_norm": 0.98046875,
|
2283 |
-
"learning_rate": 2.114027746009897e-06,
|
2284 |
-
"loss": 2.5129,
|
2285 |
-
"step": 325
|
2286 |
-
},
|
2287 |
-
{
|
2288 |
-
"epoch": 2.8384279475982535,
|
2289 |
-
"grad_norm": 0.97265625,
|
2290 |
-
"learning_rate": 2.0845477879490906e-06,
|
2291 |
-
"loss": 2.5225,
|
2292 |
-
"step": 326
|
2293 |
-
},
|
2294 |
-
{
|
2295 |
-
"epoch": 2.8471615720524017,
|
2296 |
-
"grad_norm": 1.0078125,
|
2297 |
-
"learning_rate": 2.055220595047551e-06,
|
2298 |
-
"loss": 2.5585,
|
2299 |
-
"step": 327
|
2300 |
-
},
|
2301 |
-
{
|
2302 |
-
"epoch": 2.85589519650655,
|
2303 |
-
"grad_norm": 0.92578125,
|
2304 |
-
"learning_rate": 2.0260477040045477e-06,
|
2305 |
-
"loss": 2.4975,
|
2306 |
-
"step": 328
|
2307 |
-
},
|
2308 |
-
{
|
2309 |
-
"epoch": 2.8646288209606987,
|
2310 |
-
"grad_norm": 1.046875,
|
2311 |
-
"learning_rate": 1.9970306434341806e-06,
|
2312 |
-
"loss": 2.5829,
|
2313 |
-
"step": 329
|
2314 |
-
},
|
2315 |
-
{
|
2316 |
-
"epoch": 2.8733624454148474,
|
2317 |
-
"grad_norm": 1.0078125,
|
2318 |
-
"learning_rate": 1.968170933785267e-06,
|
2319 |
-
"loss": 2.5626,
|
2320 |
-
"step": 330
|
2321 |
-
},
|
2322 |
-
{
|
2323 |
-
"epoch": 2.8820960698689957,
|
2324 |
-
"grad_norm": 0.984375,
|
2325 |
-
"learning_rate": 1.9394700872616856e-06,
|
2326 |
-
"loss": 2.4954,
|
2327 |
-
"step": 331
|
2328 |
-
},
|
2329 |
-
{
|
2330 |
-
"epoch": 2.890829694323144,
|
2331 |
-
"grad_norm": 0.953125,
|
2332 |
-
"learning_rate": 1.9109296077431373e-06,
|
2333 |
-
"loss": 2.5153,
|
2334 |
-
"step": 332
|
2335 |
-
},
|
2336 |
-
{
|
2337 |
-
"epoch": 2.8995633187772927,
|
2338 |
-
"grad_norm": 0.9453125,
|
2339 |
-
"learning_rate": 1.8825509907063328e-06,
|
2340 |
-
"loss": 2.4628,
|
2341 |
-
"step": 333
|
2342 |
-
},
|
2343 |
-
{
|
2344 |
-
"epoch": 2.908296943231441,
|
2345 |
-
"grad_norm": 1.03125,
|
2346 |
-
"learning_rate": 1.8543357231466503e-06,
|
2347 |
-
"loss": 2.6229,
|
2348 |
-
"step": 334
|
2349 |
-
},
|
2350 |
-
{
|
2351 |
-
"epoch": 2.9170305676855897,
|
2352 |
-
"grad_norm": 0.94140625,
|
2353 |
-
"learning_rate": 1.826285283500201e-06,
|
2354 |
-
"loss": 2.5758,
|
2355 |
-
"step": 335
|
2356 |
-
},
|
2357 |
-
{
|
2358 |
-
"epoch": 2.925764192139738,
|
2359 |
-
"grad_norm": 0.95703125,
|
2360 |
-
"learning_rate": 1.7984011415663754e-06,
|
2361 |
-
"loss": 2.5105,
|
2362 |
-
"step": 336
|
2363 |
-
},
|
2364 |
-
{
|
2365 |
-
"epoch": 2.934497816593886,
|
2366 |
-
"grad_norm": 1.0859375,
|
2367 |
-
"learning_rate": 1.770684758430824e-06,
|
2368 |
-
"loss": 2.5928,
|
2369 |
-
"step": 337
|
2370 |
-
},
|
2371 |
-
{
|
2372 |
-
"epoch": 2.943231441048035,
|
2373 |
-
"grad_norm": 0.953125,
|
2374 |
-
"learning_rate": 1.74313758638889e-06,
|
2375 |
-
"loss": 2.5097,
|
2376 |
-
"step": 338
|
2377 |
-
},
|
2378 |
-
{
|
2379 |
-
"epoch": 2.9519650655021836,
|
2380 |
-
"grad_norm": 0.96875,
|
2381 |
-
"learning_rate": 1.7157610688695248e-06,
|
2382 |
-
"loss": 2.5818,
|
2383 |
-
"step": 339
|
2384 |
-
},
|
2385 |
-
{
|
2386 |
-
"epoch": 2.960698689956332,
|
2387 |
-
"grad_norm": 0.94921875,
|
2388 |
-
"learning_rate": 1.6885566403596477e-06,
|
2389 |
-
"loss": 2.524,
|
2390 |
-
"step": 340
|
2391 |
-
},
|
2392 |
-
{
|
2393 |
-
"epoch": 2.96943231441048,
|
2394 |
-
"grad_norm": 0.94140625,
|
2395 |
-
"learning_rate": 1.6615257263289809e-06,
|
2396 |
-
"loss": 2.6311,
|
2397 |
-
"step": 341
|
2398 |
-
},
|
2399 |
-
{
|
2400 |
-
"epoch": 2.978165938864629,
|
2401 |
-
"grad_norm": 0.98046875,
|
2402 |
-
"learning_rate": 1.6346697431553554e-06,
|
2403 |
-
"loss": 2.5125,
|
2404 |
-
"step": 342
|
2405 |
-
},
|
2406 |
-
{
|
2407 |
-
"epoch": 2.986899563318777,
|
2408 |
-
"grad_norm": 1.0078125,
|
2409 |
-
"learning_rate": 1.607990098050501e-06,
|
2410 |
-
"loss": 2.5183,
|
2411 |
-
"step": 343
|
2412 |
-
},
|
2413 |
-
{
|
2414 |
-
"epoch": 2.995633187772926,
|
2415 |
-
"grad_norm": 1.0234375,
|
2416 |
-
"learning_rate": 1.5814881889863071e-06,
|
2417 |
-
"loss": 2.5483,
|
2418 |
-
"step": 344
|
2419 |
-
},
|
2420 |
-
{
|
2421 |
-
"epoch": 3.0,
|
2422 |
-
"grad_norm": 2.40625,
|
2423 |
-
"learning_rate": 1.555165404621567e-06,
|
2424 |
-
"loss": 2.5857,
|
2425 |
-
"step": 345
|
2426 |
-
},
|
2427 |
-
{
|
2428 |
-
"epoch": 3.0087336244541483,
|
2429 |
-
"grad_norm": 0.9921875,
|
2430 |
-
"learning_rate": 1.5290231242292231e-06,
|
2431 |
-
"loss": 2.5291,
|
2432 |
-
"step": 346
|
2433 |
-
},
|
2434 |
-
{
|
2435 |
-
"epoch": 3.017467248908297,
|
2436 |
-
"grad_norm": 0.92578125,
|
2437 |
-
"learning_rate": 1.5030627176240903e-06,
|
2438 |
-
"loss": 2.5118,
|
2439 |
-
"step": 347
|
2440 |
-
},
|
2441 |
-
{
|
2442 |
-
"epoch": 3.0262008733624453,
|
2443 |
-
"grad_norm": 1.0234375,
|
2444 |
-
"learning_rate": 1.4772855450910745e-06,
|
2445 |
-
"loss": 2.5494,
|
2446 |
-
"step": 348
|
2447 |
-
},
|
2448 |
-
{
|
2449 |
-
"epoch": 3.034934497816594,
|
2450 |
-
"grad_norm": 0.94140625,
|
2451 |
-
"learning_rate": 1.45169295731391e-06,
|
2452 |
-
"loss": 2.5181,
|
2453 |
-
"step": 349
|
2454 |
-
},
|
2455 |
-
{
|
2456 |
-
"epoch": 3.0436681222707422,
|
2457 |
-
"grad_norm": 0.953125,
|
2458 |
-
"learning_rate": 1.4262862953043677e-06,
|
2459 |
-
"loss": 2.5253,
|
2460 |
-
"step": 350
|
2461 |
-
},
|
2462 |
-
{
|
2463 |
-
"epoch": 3.052401746724891,
|
2464 |
-
"grad_norm": 1.0,
|
2465 |
-
"learning_rate": 1.4010668903320068e-06,
|
2466 |
-
"loss": 2.5927,
|
2467 |
-
"step": 351
|
2468 |
-
},
|
2469 |
-
{
|
2470 |
-
"epoch": 3.061135371179039,
|
2471 |
-
"grad_norm": 0.9765625,
|
2472 |
-
"learning_rate": 1.3760360638544012e-06,
|
2473 |
-
"loss": 2.5659,
|
2474 |
-
"step": 352
|
2475 |
-
},
|
2476 |
-
{
|
2477 |
-
"epoch": 3.069868995633188,
|
2478 |
-
"grad_norm": 0.984375,
|
2479 |
-
"learning_rate": 1.3511951274479096e-06,
|
2480 |
-
"loss": 2.5126,
|
2481 |
-
"step": 353
|
2482 |
-
},
|
2483 |
-
{
|
2484 |
-
"epoch": 3.078602620087336,
|
2485 |
-
"grad_norm": 0.96484375,
|
2486 |
-
"learning_rate": 1.326545382738948e-06,
|
2487 |
-
"loss": 2.5355,
|
2488 |
-
"step": 354
|
2489 |
-
},
|
2490 |
-
{
|
2491 |
-
"epoch": 3.087336244541485,
|
2492 |
-
"grad_norm": 0.9921875,
|
2493 |
-
"learning_rate": 1.3020881213357783e-06,
|
2494 |
-
"loss": 2.5578,
|
2495 |
-
"step": 355
|
2496 |
-
},
|
2497 |
-
{
|
2498 |
-
"epoch": 3.096069868995633,
|
2499 |
-
"grad_norm": 1.0078125,
|
2500 |
-
"learning_rate": 1.2778246247608434e-06,
|
2501 |
-
"loss": 2.5818,
|
2502 |
-
"step": 356
|
2503 |
-
},
|
2504 |
-
{
|
2505 |
-
"epoch": 3.1048034934497815,
|
2506 |
-
"grad_norm": 0.92578125,
|
2507 |
-
"learning_rate": 1.2537561643836087e-06,
|
2508 |
-
"loss": 2.5342,
|
2509 |
-
"step": 357
|
2510 |
-
},
|
2511 |
-
{
|
2512 |
-
"epoch": 3.11353711790393,
|
2513 |
-
"grad_norm": 0.9296875,
|
2514 |
-
"learning_rate": 1.2298840013539437e-06,
|
2515 |
-
"loss": 2.5346,
|
2516 |
-
"step": 358
|
2517 |
-
},
|
2518 |
-
{
|
2519 |
-
"epoch": 3.1222707423580784,
|
2520 |
-
"grad_norm": 0.98046875,
|
2521 |
-
"learning_rate": 1.2062093865360458e-06,
|
2522 |
-
"loss": 2.5297,
|
2523 |
-
"step": 359
|
2524 |
-
},
|
2525 |
-
{
|
2526 |
-
"epoch": 3.131004366812227,
|
2527 |
-
"grad_norm": 0.9921875,
|
2528 |
-
"learning_rate": 1.1827335604428914e-06,
|
2529 |
-
"loss": 2.5505,
|
2530 |
-
"step": 360
|
2531 |
-
},
|
2532 |
-
{
|
2533 |
-
"epoch": 3.1397379912663754,
|
2534 |
-
"grad_norm": 0.9609375,
|
2535 |
-
"learning_rate": 1.1594577531712392e-06,
|
2536 |
-
"loss": 2.4969,
|
2537 |
-
"step": 361
|
2538 |
-
},
|
2539 |
-
{
|
2540 |
-
"epoch": 3.148471615720524,
|
2541 |
-
"grad_norm": 1.03125,
|
2542 |
-
"learning_rate": 1.1363831843371691e-06,
|
2543 |
-
"loss": 2.5148,
|
2544 |
-
"step": 362
|
2545 |
-
},
|
2546 |
-
{
|
2547 |
-
"epoch": 3.1572052401746724,
|
2548 |
-
"grad_norm": 1.03125,
|
2549 |
-
"learning_rate": 1.1135110630121837e-06,
|
2550 |
-
"loss": 2.5036,
|
2551 |
-
"step": 363
|
2552 |
-
},
|
2553 |
-
{
|
2554 |
-
"epoch": 3.165938864628821,
|
2555 |
-
"grad_norm": 1.0,
|
2556 |
-
"learning_rate": 1.0908425876598512e-06,
|
2557 |
-
"loss": 2.5336,
|
2558 |
-
"step": 364
|
2559 |
-
},
|
2560 |
-
{
|
2561 |
-
"epoch": 3.1746724890829694,
|
2562 |
-
"grad_norm": 1.0234375,
|
2563 |
-
"learning_rate": 1.0683789460730037e-06,
|
2564 |
-
"loss": 2.4793,
|
2565 |
-
"step": 365
|
2566 |
-
},
|
2567 |
-
{
|
2568 |
-
"epoch": 3.183406113537118,
|
2569 |
-
"grad_norm": 1.0,
|
2570 |
-
"learning_rate": 1.046121315311508e-06,
|
2571 |
-
"loss": 2.6026,
|
2572 |
-
"step": 366
|
2573 |
-
},
|
2574 |
-
{
|
2575 |
-
"epoch": 3.1921397379912664,
|
2576 |
-
"grad_norm": 0.953125,
|
2577 |
-
"learning_rate": 1.0240708616405788e-06,
|
2578 |
-
"loss": 2.5879,
|
2579 |
-
"step": 367
|
2580 |
-
},
|
2581 |
-
{
|
2582 |
-
"epoch": 3.2008733624454146,
|
2583 |
-
"grad_norm": 0.984375,
|
2584 |
-
"learning_rate": 1.0022287404696774e-06,
|
2585 |
-
"loss": 2.5634,
|
2586 |
-
"step": 368
|
2587 |
-
},
|
2588 |
-
{
|
2589 |
-
"epoch": 3.2096069868995634,
|
2590 |
-
"grad_norm": 0.94140625,
|
2591 |
-
"learning_rate": 9.80596096291967e-07,
|
2592 |
-
"loss": 2.519,
|
2593 |
-
"step": 369
|
2594 |
-
},
|
2595 |
-
{
|
2596 |
-
"epoch": 3.2183406113537116,
|
2597 |
-
"grad_norm": 0.9609375,
|
2598 |
-
"learning_rate": 9.591740626243385e-07,
|
2599 |
-
"loss": 2.5288,
|
2600 |
-
"step": 370
|
2601 |
-
},
|
2602 |
-
{
|
2603 |
-
"epoch": 3.2270742358078603,
|
2604 |
-
"grad_norm": 1.015625,
|
2605 |
-
"learning_rate": 9.379637619480236e-07,
|
2606 |
-
"loss": 2.5862,
|
2607 |
-
"step": 371
|
2608 |
-
},
|
2609 |
-
{
|
2610 |
-
"epoch": 3.2358078602620086,
|
2611 |
-
"grad_norm": 0.9921875,
|
2612 |
-
"learning_rate": 9.169663056497713e-07,
|
2613 |
-
"loss": 2.5689,
|
2614 |
-
"step": 372
|
2615 |
-
},
|
2616 |
-
{
|
2617 |
-
"epoch": 3.2445414847161573,
|
2618 |
-
"grad_norm": 0.94140625,
|
2619 |
-
"learning_rate": 8.961827939636198e-07,
|
2620 |
-
"loss": 2.5284,
|
2621 |
-
"step": 373
|
2622 |
-
},
|
2623 |
-
{
|
2624 |
-
"epoch": 3.2532751091703056,
|
2625 |
-
"grad_norm": 0.9453125,
|
2626 |
-
"learning_rate": 8.756143159132391e-07,
|
2627 |
-
"loss": 2.5511,
|
2628 |
-
"step": 374
|
2629 |
-
},
|
2630 |
-
{
|
2631 |
-
"epoch": 3.2620087336244543,
|
2632 |
-
"grad_norm": 1.0234375,
|
2633 |
-
"learning_rate": 8.552619492548736e-07,
|
2634 |
-
"loss": 2.4898,
|
2635 |
-
"step": 375
|
2636 |
-
},
|
2637 |
-
{
|
2638 |
-
"epoch": 3.2707423580786026,
|
2639 |
-
"grad_norm": 0.95703125,
|
2640 |
-
"learning_rate": 8.351267604208674e-07,
|
2641 |
-
"loss": 2.5291,
|
2642 |
-
"step": 376
|
2643 |
-
},
|
2644 |
-
{
|
2645 |
-
"epoch": 3.279475982532751,
|
2646 |
-
"grad_norm": 0.94921875,
|
2647 |
-
"learning_rate": 8.15209804463783e-07,
|
2648 |
-
"loss": 2.5229,
|
2649 |
-
"step": 377
|
2650 |
-
},
|
2651 |
-
{
|
2652 |
-
"epoch": 3.2882096069868996,
|
2653 |
-
"grad_norm": 0.94921875,
|
2654 |
-
"learning_rate": 7.955121250011217e-07,
|
2655 |
-
"loss": 2.4944,
|
2656 |
-
"step": 378
|
2657 |
-
},
|
2658 |
-
{
|
2659 |
-
"epoch": 3.2969432314410483,
|
2660 |
-
"grad_norm": 0.984375,
|
2661 |
-
"learning_rate": 7.760347541606339e-07,
|
2662 |
-
"loss": 2.5123,
|
2663 |
-
"step": 379
|
2664 |
-
},
|
2665 |
-
{
|
2666 |
-
"epoch": 3.3056768558951966,
|
2667 |
-
"grad_norm": 1.0390625,
|
2668 |
-
"learning_rate": 7.567787125262449e-07,
|
2669 |
-
"loss": 2.5242,
|
2670 |
-
"step": 380
|
2671 |
-
},
|
2672 |
-
{
|
2673 |
-
"epoch": 3.314410480349345,
|
2674 |
-
"grad_norm": 0.9921875,
|
2675 |
-
"learning_rate": 7.377450090845733e-07,
|
2676 |
-
"loss": 2.547,
|
2677 |
-
"step": 381
|
2678 |
-
},
|
2679 |
-
{
|
2680 |
-
"epoch": 3.3231441048034935,
|
2681 |
-
"grad_norm": 0.94140625,
|
2682 |
-
"learning_rate": 7.189346411720604e-07,
|
2683 |
-
"loss": 2.5564,
|
2684 |
-
"step": 382
|
2685 |
-
},
|
2686 |
-
{
|
2687 |
-
"epoch": 3.331877729257642,
|
2688 |
-
"grad_norm": 0.95703125,
|
2689 |
-
"learning_rate": 7.003485944227162e-07,
|
2690 |
-
"loss": 2.4298,
|
2691 |
-
"step": 383
|
2692 |
-
},
|
2693 |
-
{
|
2694 |
-
"epoch": 3.3406113537117905,
|
2695 |
-
"grad_norm": 0.9296875,
|
2696 |
-
"learning_rate": 6.819878427164667e-07,
|
2697 |
-
"loss": 2.5536,
|
2698 |
-
"step": 384
|
2699 |
-
},
|
2700 |
-
{
|
2701 |
-
"epoch": 3.349344978165939,
|
2702 |
-
"grad_norm": 0.9609375,
|
2703 |
-
"learning_rate": 6.638533481281323e-07,
|
2704 |
-
"loss": 2.5311,
|
2705 |
-
"step": 385
|
2706 |
-
},
|
2707 |
-
{
|
2708 |
-
"epoch": 3.3580786026200875,
|
2709 |
-
"grad_norm": 0.93359375,
|
2710 |
-
"learning_rate": 6.459460608770113e-07,
|
2711 |
-
"loss": 2.4999,
|
2712 |
-
"step": 386
|
2713 |
-
},
|
2714 |
-
{
|
2715 |
-
"epoch": 3.3668122270742358,
|
2716 |
-
"grad_norm": 0.9453125,
|
2717 |
-
"learning_rate": 6.282669192770896e-07,
|
2718 |
-
"loss": 2.5976,
|
2719 |
-
"step": 387
|
2720 |
-
},
|
2721 |
-
{
|
2722 |
-
"epoch": 3.3755458515283845,
|
2723 |
-
"grad_norm": 0.9765625,
|
2724 |
-
"learning_rate": 6.108168496878781e-07,
|
2725 |
-
"loss": 2.5356,
|
2726 |
-
"step": 388
|
2727 |
-
},
|
2728 |
-
{
|
2729 |
-
"epoch": 3.3842794759825328,
|
2730 |
-
"grad_norm": 0.9921875,
|
2731 |
-
"learning_rate": 5.935967664658682e-07,
|
2732 |
-
"loss": 2.5716,
|
2733 |
-
"step": 389
|
2734 |
-
},
|
2735 |
-
{
|
2736 |
-
"epoch": 3.393013100436681,
|
2737 |
-
"grad_norm": 0.9375,
|
2738 |
-
"learning_rate": 5.766075719166276e-07,
|
2739 |
-
"loss": 2.6072,
|
2740 |
-
"step": 390
|
2741 |
-
},
|
2742 |
-
{
|
2743 |
-
"epoch": 3.4017467248908297,
|
2744 |
-
"grad_norm": 0.9453125,
|
2745 |
-
"learning_rate": 5.598501562475111e-07,
|
2746 |
-
"loss": 2.5212,
|
2747 |
-
"step": 391
|
2748 |
-
},
|
2749 |
-
{
|
2750 |
-
"epoch": 3.410480349344978,
|
2751 |
-
"grad_norm": 0.953125,
|
2752 |
-
"learning_rate": 5.433253975210262e-07,
|
2753 |
-
"loss": 2.5536,
|
2754 |
-
"step": 392
|
2755 |
-
},
|
2756 |
-
{
|
2757 |
-
"epoch": 3.4192139737991267,
|
2758 |
-
"grad_norm": 0.953125,
|
2759 |
-
"learning_rate": 5.270341616088153e-07,
|
2760 |
-
"loss": 2.552,
|
2761 |
-
"step": 393
|
2762 |
-
},
|
2763 |
-
{
|
2764 |
-
"epoch": 3.427947598253275,
|
2765 |
-
"grad_norm": 0.9765625,
|
2766 |
-
"learning_rate": 5.109773021462921e-07,
|
2767 |
-
"loss": 2.5479,
|
2768 |
-
"step": 394
|
2769 |
-
},
|
2770 |
-
{
|
2771 |
-
"epoch": 3.4366812227074237,
|
2772 |
-
"grad_norm": 0.94140625,
|
2773 |
-
"learning_rate": 4.951556604879049e-07,
|
2774 |
-
"loss": 2.5405,
|
2775 |
-
"step": 395
|
2776 |
-
},
|
2777 |
-
{
|
2778 |
-
"epoch": 3.445414847161572,
|
2779 |
-
"grad_norm": 0.99609375,
|
2780 |
-
"learning_rate": 4.795700656630569e-07,
|
2781 |
-
"loss": 2.5673,
|
2782 |
-
"step": 396
|
2783 |
-
},
|
2784 |
-
{
|
2785 |
-
"epoch": 3.4541484716157207,
|
2786 |
-
"grad_norm": 0.95703125,
|
2787 |
-
"learning_rate": 4.6422133433266513e-07,
|
2788 |
-
"loss": 2.6057,
|
2789 |
-
"step": 397
|
2790 |
-
},
|
2791 |
-
{
|
2792 |
-
"epoch": 3.462882096069869,
|
2793 |
-
"grad_norm": 0.98046875,
|
2794 |
-
"learning_rate": 4.49110270746369e-07,
|
2795 |
-
"loss": 2.5215,
|
2796 |
-
"step": 398
|
2797 |
-
},
|
2798 |
-
{
|
2799 |
-
"epoch": 3.4716157205240172,
|
2800 |
-
"grad_norm": 0.9765625,
|
2801 |
-
"learning_rate": 4.342376667003845e-07,
|
2802 |
-
"loss": 2.5393,
|
2803 |
-
"step": 399
|
2804 |
-
},
|
2805 |
-
{
|
2806 |
-
"epoch": 3.480349344978166,
|
2807 |
-
"grad_norm": 1.046875,
|
2808 |
-
"learning_rate": 4.1960430149602213e-07,
|
2809 |
-
"loss": 2.5921,
|
2810 |
-
"step": 400
|
2811 |
-
},
|
2812 |
-
{
|
2813 |
-
"epoch": 3.489082969432314,
|
2814 |
-
"grad_norm": 0.9375,
|
2815 |
-
"learning_rate": 4.05210941898847e-07,
|
2816 |
-
"loss": 2.4926,
|
2817 |
-
"step": 401
|
2818 |
-
},
|
2819 |
-
{
|
2820 |
-
"epoch": 3.497816593886463,
|
2821 |
-
"grad_norm": 0.95703125,
|
2822 |
-
"learning_rate": 3.9105834209850536e-07,
|
2823 |
-
"loss": 2.6581,
|
2824 |
-
"step": 402
|
2825 |
-
},
|
2826 |
-
{
|
2827 |
-
"epoch": 3.506550218340611,
|
2828 |
-
"grad_norm": 0.94140625,
|
2829 |
-
"learning_rate": 3.771472436692053e-07,
|
2830 |
-
"loss": 2.5217,
|
2831 |
-
"step": 403
|
2832 |
-
},
|
2833 |
-
{
|
2834 |
-
"epoch": 3.51528384279476,
|
2835 |
-
"grad_norm": 1.0078125,
|
2836 |
-
"learning_rate": 3.634783755308563e-07,
|
2837 |
-
"loss": 2.5149,
|
2838 |
-
"step": 404
|
2839 |
-
},
|
2840 |
-
{
|
2841 |
-
"epoch": 3.524017467248908,
|
2842 |
-
"grad_norm": 1.0078125,
|
2843 |
-
"learning_rate": 3.500524539108807e-07,
|
2844 |
-
"loss": 2.5651,
|
2845 |
-
"step": 405
|
2846 |
-
},
|
2847 |
-
{
|
2848 |
-
"epoch": 3.532751091703057,
|
2849 |
-
"grad_norm": 0.9609375,
|
2850 |
-
"learning_rate": 3.3687018230667833e-07,
|
2851 |
-
"loss": 2.5981,
|
2852 |
-
"step": 406
|
2853 |
-
},
|
2854 |
-
{
|
2855 |
-
"epoch": 3.541484716157205,
|
2856 |
-
"grad_norm": 0.91015625,
|
2857 |
-
"learning_rate": 3.239322514487686e-07,
|
2858 |
-
"loss": 2.4766,
|
2859 |
-
"step": 407
|
2860 |
-
},
|
2861 |
-
{
|
2862 |
-
"epoch": 3.5502183406113534,
|
2863 |
-
"grad_norm": 0.97265625,
|
2864 |
-
"learning_rate": 3.112393392645985e-07,
|
2865 |
-
"loss": 2.4867,
|
2866 |
-
"step": 408
|
2867 |
-
},
|
2868 |
-
{
|
2869 |
-
"epoch": 3.558951965065502,
|
2870 |
-
"grad_norm": 0.94140625,
|
2871 |
-
"learning_rate": 2.9879211084301194e-07,
|
2872 |
-
"loss": 2.5488,
|
2873 |
-
"step": 409
|
2874 |
-
},
|
2875 |
-
{
|
2876 |
-
"epoch": 3.567685589519651,
|
2877 |
-
"grad_norm": 1.0,
|
2878 |
-
"learning_rate": 2.8659121839941293e-07,
|
2879 |
-
"loss": 2.5341,
|
2880 |
-
"step": 410
|
2881 |
-
},
|
2882 |
-
{
|
2883 |
-
"epoch": 3.576419213973799,
|
2884 |
-
"grad_norm": 1.03125,
|
2885 |
-
"learning_rate": 2.7463730124157706e-07,
|
2886 |
-
"loss": 2.606,
|
2887 |
-
"step": 411
|
2888 |
-
},
|
2889 |
-
{
|
2890 |
-
"epoch": 3.5851528384279474,
|
2891 |
-
"grad_norm": 0.97265625,
|
2892 |
-
"learning_rate": 2.629309857361639e-07,
|
2893 |
-
"loss": 2.512,
|
2894 |
-
"step": 412
|
2895 |
-
},
|
2896 |
-
{
|
2897 |
-
"epoch": 3.593886462882096,
|
2898 |
-
"grad_norm": 0.97265625,
|
2899 |
-
"learning_rate": 2.5147288527588964e-07,
|
2900 |
-
"loss": 2.5638,
|
2901 |
-
"step": 413
|
2902 |
-
},
|
2903 |
-
{
|
2904 |
-
"epoch": 3.6026200873362444,
|
2905 |
-
"grad_norm": 0.94140625,
|
2906 |
-
"learning_rate": 2.4026360024738904e-07,
|
2907 |
-
"loss": 2.5113,
|
2908 |
-
"step": 414
|
2909 |
-
},
|
2910 |
-
{
|
2911 |
-
"epoch": 3.611353711790393,
|
2912 |
-
"grad_norm": 0.98046875,
|
2913 |
-
"learning_rate": 2.2930371799975593e-07,
|
2914 |
-
"loss": 2.5619,
|
2915 |
-
"step": 415
|
2916 |
-
},
|
2917 |
-
{
|
2918 |
-
"epoch": 3.6200873362445414,
|
2919 |
-
"grad_norm": 0.91796875,
|
2920 |
-
"learning_rate": 2.1859381281376436e-07,
|
2921 |
-
"loss": 2.4561,
|
2922 |
-
"step": 416
|
2923 |
-
},
|
2924 |
-
{
|
2925 |
-
"epoch": 3.62882096069869,
|
2926 |
-
"grad_norm": 0.94140625,
|
2927 |
-
"learning_rate": 2.0813444587178156e-07,
|
2928 |
-
"loss": 2.435,
|
2929 |
-
"step": 417
|
2930 |
-
},
|
2931 |
-
{
|
2932 |
-
"epoch": 3.6375545851528384,
|
2933 |
-
"grad_norm": 0.92578125,
|
2934 |
-
"learning_rate": 1.9792616522835872e-07,
|
2935 |
-
"loss": 2.5178,
|
2936 |
-
"step": 418
|
2937 |
-
},
|
2938 |
-
{
|
2939 |
-
"epoch": 3.646288209606987,
|
2940 |
-
"grad_norm": 1.0078125,
|
2941 |
-
"learning_rate": 1.8796950578151785e-07,
|
2942 |
-
"loss": 2.538,
|
2943 |
-
"step": 419
|
2944 |
-
},
|
2945 |
-
{
|
2946 |
-
"epoch": 3.6550218340611353,
|
2947 |
-
"grad_norm": 0.94140625,
|
2948 |
-
"learning_rate": 1.7826498924472135e-07,
|
2949 |
-
"loss": 2.5299,
|
2950 |
-
"step": 420
|
2951 |
-
},
|
2952 |
-
{
|
2953 |
-
"epoch": 3.6637554585152836,
|
2954 |
-
"grad_norm": 0.9609375,
|
2955 |
-
"learning_rate": 1.6881312411953288e-07,
|
2956 |
-
"loss": 2.5165,
|
2957 |
-
"step": 421
|
2958 |
-
},
|
2959 |
-
{
|
2960 |
-
"epoch": 3.6724890829694323,
|
2961 |
-
"grad_norm": 0.93359375,
|
2962 |
-
"learning_rate": 1.5961440566897913e-07,
|
2963 |
-
"loss": 2.5531,
|
2964 |
-
"step": 422
|
2965 |
-
},
|
2966 |
-
{
|
2967 |
-
"epoch": 3.681222707423581,
|
2968 |
-
"grad_norm": 0.95703125,
|
2969 |
-
"learning_rate": 1.5066931589159118e-07,
|
2970 |
-
"loss": 2.4546,
|
2971 |
-
"step": 423
|
2972 |
-
},
|
2973 |
-
{
|
2974 |
-
"epoch": 3.6899563318777293,
|
2975 |
-
"grad_norm": 0.97265625,
|
2976 |
-
"learning_rate": 1.4197832349615525e-07,
|
2977 |
-
"loss": 2.5602,
|
2978 |
-
"step": 424
|
2979 |
-
},
|
2980 |
-
{
|
2981 |
-
"epoch": 3.6986899563318776,
|
2982 |
-
"grad_norm": 0.93359375,
|
2983 |
-
"learning_rate": 1.3354188387715017e-07,
|
2984 |
-
"loss": 2.5096,
|
2985 |
-
"step": 425
|
2986 |
-
},
|
2987 |
-
{
|
2988 |
-
"epoch": 3.7074235807860263,
|
2989 |
-
"grad_norm": 0.93359375,
|
2990 |
-
"learning_rate": 1.253604390908819e-07,
|
2991 |
-
"loss": 2.502,
|
2992 |
-
"step": 426
|
2993 |
-
},
|
2994 |
-
{
|
2995 |
-
"epoch": 3.7161572052401746,
|
2996 |
-
"grad_norm": 1.0078125,
|
2997 |
-
"learning_rate": 1.174344178323289e-07,
|
2998 |
-
"loss": 2.5566,
|
2999 |
-
"step": 427
|
3000 |
-
},
|
3001 |
-
{
|
3002 |
-
"epoch": 3.7248908296943233,
|
3003 |
-
"grad_norm": 0.9453125,
|
3004 |
-
"learning_rate": 1.0976423541266934e-07,
|
3005 |
-
"loss": 2.5827,
|
3006 |
-
"step": 428
|
3007 |
-
},
|
3008 |
-
{
|
3009 |
-
"epoch": 3.7336244541484715,
|
3010 |
-
"grad_norm": 0.9609375,
|
3011 |
-
"learning_rate": 1.0235029373752758e-07,
|
3012 |
-
"loss": 2.5091,
|
3013 |
-
"step": 429
|
3014 |
-
},
|
3015 |
-
{
|
3016 |
-
"epoch": 3.74235807860262,
|
3017 |
-
"grad_norm": 0.93359375,
|
3018 |
-
"learning_rate": 9.519298128591092e-08,
|
3019 |
-
"loss": 2.558,
|
3020 |
-
"step": 430
|
3021 |
-
},
|
3022 |
-
{
|
3023 |
-
"epoch": 3.7510917030567685,
|
3024 |
-
"grad_norm": 0.9140625,
|
3025 |
-
"learning_rate": 8.829267308985535e-08,
|
3026 |
-
"loss": 2.542,
|
3027 |
-
"step": 431
|
3028 |
-
},
|
3029 |
-
{
|
3030 |
-
"epoch": 3.7598253275109172,
|
3031 |
-
"grad_norm": 0.984375,
|
3032 |
-
"learning_rate": 8.164973071477178e-08,
|
3033 |
-
"loss": 2.5471,
|
3034 |
-
"step": 432
|
3035 |
-
},
|
3036 |
-
{
|
3037 |
-
"epoch": 3.7685589519650655,
|
3038 |
-
"grad_norm": 0.95703125,
|
3039 |
-
"learning_rate": 7.526450224050407e-08,
|
3040 |
-
"loss": 2.5799,
|
3041 |
-
"step": 433
|
3042 |
-
},
|
3043 |
-
{
|
3044 |
-
"epoch": 3.777292576419214,
|
3045 |
-
"grad_norm": 0.99609375,
|
3046 |
-
"learning_rate": 6.913732224308855e-08,
|
3047 |
-
"loss": 2.5495,
|
3048 |
-
"step": 434
|
3049 |
-
},
|
3050 |
-
{
|
3051 |
-
"epoch": 3.7860262008733625,
|
3052 |
-
"grad_norm": 0.91015625,
|
3053 |
-
"learning_rate": 6.326851177722304e-08,
|
3054 |
-
"loss": 2.523,
|
3055 |
-
"step": 435
|
3056 |
-
},
|
3057 |
-
{
|
3058 |
-
"epoch": 3.7947598253275108,
|
3059 |
-
"grad_norm": 0.94140625,
|
3060 |
-
"learning_rate": 5.7658378359443104e-08,
|
3061 |
-
"loss": 2.5042,
|
3062 |
-
"step": 436
|
3063 |
-
},
|
3064 |
-
{
|
3065 |
-
"epoch": 3.8034934497816595,
|
3066 |
-
"grad_norm": 0.9609375,
|
3067 |
-
"learning_rate": 5.230721595201049e-08,
|
3068 |
-
"loss": 2.5882,
|
3069 |
-
"step": 437
|
3070 |
-
},
|
3071 |
-
{
|
3072 |
-
"epoch": 3.8122270742358078,
|
3073 |
-
"grad_norm": 0.97265625,
|
3074 |
-
"learning_rate": 4.7215304947508254e-08,
|
3075 |
-
"loss": 2.506,
|
3076 |
-
"step": 438
|
3077 |
-
},
|
3078 |
-
{
|
3079 |
-
"epoch": 3.8209606986899565,
|
3080 |
-
"grad_norm": 0.984375,
|
3081 |
-
"learning_rate": 4.2382912154150244e-08,
|
3082 |
-
"loss": 2.4979,
|
3083 |
-
"step": 439
|
3084 |
-
},
|
3085 |
-
{
|
3086 |
-
"epoch": 3.8296943231441047,
|
3087 |
-
"grad_norm": 0.91015625,
|
3088 |
-
"learning_rate": 3.781029078179843e-08,
|
3089 |
-
"loss": 2.5049,
|
3090 |
-
"step": 440
|
3091 |
-
},
|
3092 |
-
{
|
3093 |
-
"epoch": 3.8384279475982535,
|
3094 |
-
"grad_norm": 0.98828125,
|
3095 |
-
"learning_rate": 3.3497680428697943e-08,
|
3096 |
-
"loss": 2.5263,
|
3097 |
-
"step": 441
|
3098 |
-
},
|
3099 |
-
{
|
3100 |
-
"epoch": 3.8471615720524017,
|
3101 |
-
"grad_norm": 0.94921875,
|
3102 |
-
"learning_rate": 2.944530706892046e-08,
|
3103 |
-
"loss": 2.5072,
|
3104 |
-
"step": 442
|
3105 |
-
},
|
3106 |
-
{
|
3107 |
-
"epoch": 3.85589519650655,
|
3108 |
-
"grad_norm": 0.9453125,
|
3109 |
-
"learning_rate": 2.5653383040524228e-08,
|
3110 |
-
"loss": 2.5696,
|
3111 |
-
"step": 443
|
3112 |
-
},
|
3113 |
-
{
|
3114 |
-
"epoch": 3.8646288209606987,
|
3115 |
-
"grad_norm": 0.94140625,
|
3116 |
-
"learning_rate": 2.212210703442852e-08,
|
3117 |
-
"loss": 2.5659,
|
3118 |
-
"step": 444
|
3119 |
-
},
|
3120 |
-
{
|
3121 |
-
"epoch": 3.8733624454148474,
|
3122 |
-
"grad_norm": 0.953125,
|
3123 |
-
"learning_rate": 1.8851664083999742e-08,
|
3124 |
-
"loss": 2.5242,
|
3125 |
-
"step": 445
|
3126 |
-
},
|
3127 |
-
{
|
3128 |
-
"epoch": 3.8820960698689957,
|
3129 |
-
"grad_norm": 1.0078125,
|
3130 |
-
"learning_rate": 1.58422255553603e-08,
|
3131 |
-
"loss": 2.5726,
|
3132 |
-
"step": 446
|
3133 |
-
},
|
3134 |
-
{
|
3135 |
-
"epoch": 3.890829694323144,
|
3136 |
-
"grad_norm": 0.97265625,
|
3137 |
-
"learning_rate": 1.3093949138406892e-08,
|
3138 |
-
"loss": 2.5634,
|
3139 |
-
"step": 447
|
3140 |
-
},
|
3141 |
-
{
|
3142 |
-
"epoch": 3.8995633187772927,
|
3143 |
-
"grad_norm": 0.98046875,
|
3144 |
-
"learning_rate": 1.0606978838545445e-08,
|
3145 |
-
"loss": 2.5239,
|
3146 |
-
"step": 448
|
3147 |
-
},
|
3148 |
-
{
|
3149 |
-
"epoch": 3.908296943231441,
|
3150 |
-
"grad_norm": 0.984375,
|
3151 |
-
"learning_rate": 8.381444969151608e-09,
|
3152 |
-
"loss": 2.5887,
|
3153 |
-
"step": 449
|
3154 |
-
},
|
3155 |
-
{
|
3156 |
-
"epoch": 3.9170305676855897,
|
3157 |
-
"grad_norm": 0.98046875,
|
3158 |
-
"learning_rate": 6.417464144736208e-09,
|
3159 |
-
"loss": 2.5814,
|
3160 |
-
"step": 450
|
3161 |
-
},
|
3162 |
-
{
|
3163 |
-
"epoch": 3.925764192139738,
|
3164 |
-
"grad_norm": 0.921875,
|
3165 |
-
"learning_rate": 4.7151392748379095e-09,
|
3166 |
-
"loss": 2.5465,
|
3167 |
-
"step": 451
|
3168 |
-
},
|
3169 |
-
{
|
3170 |
-
"epoch": 3.934497816593886,
|
3171 |
-
"grad_norm": 0.96484375,
|
3172 |
-
"learning_rate": 3.2745595586319843e-09,
|
3173 |
-
"loss": 2.5138,
|
3174 |
-
"step": 452
|
3175 |
-
},
|
3176 |
-
{
|
3177 |
-
"epoch": 3.943231441048035,
|
3178 |
-
"grad_norm": 0.96484375,
|
3179 |
-
"learning_rate": 2.0958004802529297e-09,
|
3180 |
-
"loss": 2.5643,
|
3181 |
-
"step": 453
|
3182 |
-
},
|
3183 |
-
{
|
3184 |
-
"epoch": 3.9519650655021836,
|
3185 |
-
"grad_norm": 0.9765625,
|
3186 |
-
"learning_rate": 1.1789238048431905e-09,
|
3187 |
-
"loss": 2.5418,
|
3188 |
-
"step": 454
|
3189 |
-
},
|
3190 |
-
{
|
3191 |
-
"epoch": 3.960698689956332,
|
3192 |
-
"grad_norm": 0.9296875,
|
3193 |
-
"learning_rate": 5.239775753129728e-10,
|
3194 |
-
"loss": 2.4993,
|
3195 |
-
"step": 455
|
3196 |
-
},
|
3197 |
-
{
|
3198 |
-
"epoch": 3.96943231441048,
|
3199 |
-
"grad_norm": 1.0078125,
|
3200 |
-
"learning_rate": 1.3099610982614254e-10,
|
3201 |
-
"loss": 2.4706,
|
3202 |
-
"step": 456
|
3203 |
-
}
|
3204 |
-
],
|
3205 |
-
"logging_steps": 1,
|
3206 |
-
"max_steps": 456,
|
3207 |
-
"num_input_tokens_seen": 0,
|
3208 |
-
"num_train_epochs": 4,
|
3209 |
-
"save_steps": 114,
|
3210 |
-
"stateful_callbacks": {
|
3211 |
-
"TrainerControl": {
|
3212 |
-
"args": {
|
3213 |
-
"should_epoch_stop": false,
|
3214 |
-
"should_evaluate": false,
|
3215 |
-
"should_log": false,
|
3216 |
-
"should_save": true,
|
3217 |
-
"should_training_stop": true
|
3218 |
-
},
|
3219 |
-
"attributes": {}
|
3220 |
-
}
|
3221 |
-
},
|
3222 |
-
"total_flos": 1.4249514265214976e+18,
|
3223 |
-
"train_batch_size": 2,
|
3224 |
-
"trial_name": null,
|
3225 |
-
"trial_params": null
|
3226 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-456/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ae0592bc0dda5ec7f7a3ef05f7a468bec687ffdab3262199ff4c718485bd04da
|
3 |
-
size 6520
|
|
|
|
|
|
|
|
checkpoint-456/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|