Training in progress, step 141, checkpoint
Browse files- checkpoint-141/added_tokens.json +5 -0
- checkpoint-141/chat_template.jinja +4 -0
- checkpoint-141/config.json +32 -0
- checkpoint-141/generation_config.json +9 -0
- checkpoint-141/merges.txt +0 -0
- checkpoint-141/model-00001-of-00002.safetensors +3 -0
- checkpoint-141/model-00002-of-00002.safetensors +3 -0
- checkpoint-141/model.safetensors.index.json +261 -0
- checkpoint-141/optimizer.pt +3 -0
- checkpoint-141/rng_state.pth +3 -0
- checkpoint-141/scheduler.pt +3 -0
- checkpoint-141/special_tokens_map.json +30 -0
- checkpoint-141/tokenizer.json +0 -0
- checkpoint-141/tokenizer_config.json +69 -0
- checkpoint-141/trainer_state.json +1021 -0
- checkpoint-141/training_args.bin +3 -0
- checkpoint-141/vocab.json +0 -0
checkpoint-141/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endofprompt|>": 100276,
|
3 |
+
"<|im_end|>": 100265,
|
4 |
+
"<|im_start|>": 100264
|
5 |
+
}
|
checkpoint-141/chat_template.jinja
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
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-141/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-141/generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-141/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-141/model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fdd07bf5ce443f8e60d55a5b391253eed234f270782bac8b9c114e72e17f86d
|
3 |
+
size 4983077832
|
checkpoint-141/model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:962c4cfabce6cd2afc02357983b04c8b474f30c79cfbae5384b281acb20a7795
|
3 |
+
size 3842234168
|
checkpoint-141/model.safetensors.index.json
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-141/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40cd84cf6aa0350183d4bc0338c36f53416a4425c9dae3beee0c11c33cff2d61
|
3 |
+
size 11466962878
|
checkpoint-141/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
|
3 |
+
size 14244
|
checkpoint-141/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81d3b77a80be28ba7fd7bced065afe839678d65a68f497cb71e6167b4dfd4974
|
3 |
+
size 1064
|
checkpoint-141/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-141/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-141/tokenizer_config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-141/trainer_state.json
ADDED
@@ -0,0 +1,1021 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.9964664310954063,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 141,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.007067137809187279,
|
14 |
+
"grad_norm": 1.2265625,
|
15 |
+
"learning_rate": 0.0,
|
16 |
+
"loss": 1.9174,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.014134275618374558,
|
21 |
+
"grad_norm": 1.0234375,
|
22 |
+
"learning_rate": 3.5714285714285716e-07,
|
23 |
+
"loss": 2.2074,
|
24 |
+
"step": 2
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.02120141342756184,
|
28 |
+
"grad_norm": 1.2421875,
|
29 |
+
"learning_rate": 7.142857142857143e-07,
|
30 |
+
"loss": 1.7854,
|
31 |
+
"step": 3
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.028268551236749116,
|
35 |
+
"grad_norm": 1.1484375,
|
36 |
+
"learning_rate": 1.0714285714285714e-06,
|
37 |
+
"loss": 2.1768,
|
38 |
+
"step": 4
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0353356890459364,
|
42 |
+
"grad_norm": 0.9375,
|
43 |
+
"learning_rate": 1.4285714285714286e-06,
|
44 |
+
"loss": 2.1438,
|
45 |
+
"step": 5
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.04240282685512368,
|
49 |
+
"grad_norm": 3.484375,
|
50 |
+
"learning_rate": 1.7857142857142859e-06,
|
51 |
+
"loss": 2.5976,
|
52 |
+
"step": 6
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.04946996466431095,
|
56 |
+
"grad_norm": 1.2265625,
|
57 |
+
"learning_rate": 2.1428571428571427e-06,
|
58 |
+
"loss": 2.2351,
|
59 |
+
"step": 7
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.05653710247349823,
|
63 |
+
"grad_norm": 0.984375,
|
64 |
+
"learning_rate": 2.5e-06,
|
65 |
+
"loss": 2.0092,
|
66 |
+
"step": 8
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.0636042402826855,
|
70 |
+
"grad_norm": 1.1015625,
|
71 |
+
"learning_rate": 2.8571428571428573e-06,
|
72 |
+
"loss": 2.1347,
|
73 |
+
"step": 9
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.0706713780918728,
|
77 |
+
"grad_norm": 1.03125,
|
78 |
+
"learning_rate": 3.2142857142857147e-06,
|
79 |
+
"loss": 2.0748,
|
80 |
+
"step": 10
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.07773851590106007,
|
84 |
+
"grad_norm": 0.9140625,
|
85 |
+
"learning_rate": 3.5714285714285718e-06,
|
86 |
+
"loss": 1.7444,
|
87 |
+
"step": 11
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.08480565371024736,
|
91 |
+
"grad_norm": 0.83984375,
|
92 |
+
"learning_rate": 3.928571428571429e-06,
|
93 |
+
"loss": 1.5372,
|
94 |
+
"step": 12
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.09187279151943463,
|
98 |
+
"grad_norm": 0.71484375,
|
99 |
+
"learning_rate": 4.2857142857142855e-06,
|
100 |
+
"loss": 1.4944,
|
101 |
+
"step": 13
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.0989399293286219,
|
105 |
+
"grad_norm": 0.8046875,
|
106 |
+
"learning_rate": 4.642857142857144e-06,
|
107 |
+
"loss": 1.8555,
|
108 |
+
"step": 14
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.10600706713780919,
|
112 |
+
"grad_norm": 0.92578125,
|
113 |
+
"learning_rate": 5e-06,
|
114 |
+
"loss": 1.5569,
|
115 |
+
"step": 15
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.11307420494699646,
|
119 |
+
"grad_norm": 1.34375,
|
120 |
+
"learning_rate": 5.357142857142857e-06,
|
121 |
+
"loss": 2.1602,
|
122 |
+
"step": 16
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.12014134275618374,
|
126 |
+
"grad_norm": 0.84375,
|
127 |
+
"learning_rate": 5.7142857142857145e-06,
|
128 |
+
"loss": 2.0495,
|
129 |
+
"step": 17
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.127208480565371,
|
133 |
+
"grad_norm": 2.9375,
|
134 |
+
"learning_rate": 6.071428571428571e-06,
|
135 |
+
"loss": 2.2094,
|
136 |
+
"step": 18
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.13427561837455831,
|
140 |
+
"grad_norm": 0.8046875,
|
141 |
+
"learning_rate": 6.4285714285714295e-06,
|
142 |
+
"loss": 1.3931,
|
143 |
+
"step": 19
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.1413427561837456,
|
147 |
+
"grad_norm": 0.71875,
|
148 |
+
"learning_rate": 6.785714285714287e-06,
|
149 |
+
"loss": 1.7009,
|
150 |
+
"step": 20
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.14840989399293286,
|
154 |
+
"grad_norm": 0.859375,
|
155 |
+
"learning_rate": 7.1428571428571436e-06,
|
156 |
+
"loss": 1.8362,
|
157 |
+
"step": 21
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.15547703180212014,
|
161 |
+
"grad_norm": 0.67578125,
|
162 |
+
"learning_rate": 7.500000000000001e-06,
|
163 |
+
"loss": 1.9375,
|
164 |
+
"step": 22
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.1625441696113074,
|
168 |
+
"grad_norm": 0.9765625,
|
169 |
+
"learning_rate": 7.857142857142858e-06,
|
170 |
+
"loss": 2.1988,
|
171 |
+
"step": 23
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.1696113074204947,
|
175 |
+
"grad_norm": 0.71484375,
|
176 |
+
"learning_rate": 8.214285714285714e-06,
|
177 |
+
"loss": 1.7918,
|
178 |
+
"step": 24
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.17667844522968199,
|
182 |
+
"grad_norm": 1.0234375,
|
183 |
+
"learning_rate": 8.571428571428571e-06,
|
184 |
+
"loss": 2.1915,
|
185 |
+
"step": 25
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.18374558303886926,
|
189 |
+
"grad_norm": 0.796875,
|
190 |
+
"learning_rate": 8.92857142857143e-06,
|
191 |
+
"loss": 2.3101,
|
192 |
+
"step": 26
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.19081272084805653,
|
196 |
+
"grad_norm": 0.71875,
|
197 |
+
"learning_rate": 9.285714285714288e-06,
|
198 |
+
"loss": 1.9351,
|
199 |
+
"step": 27
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.1978798586572438,
|
203 |
+
"grad_norm": 1.4296875,
|
204 |
+
"learning_rate": 9.642857142857144e-06,
|
205 |
+
"loss": 1.7059,
|
206 |
+
"step": 28
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.2049469964664311,
|
210 |
+
"grad_norm": 0.7734375,
|
211 |
+
"learning_rate": 1e-05,
|
212 |
+
"loss": 2.1424,
|
213 |
+
"step": 29
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.21201413427561838,
|
217 |
+
"grad_norm": 0.6328125,
|
218 |
+
"learning_rate": 9.999914116658896e-06,
|
219 |
+
"loss": 1.7643,
|
220 |
+
"step": 30
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.21908127208480566,
|
224 |
+
"grad_norm": 0.79296875,
|
225 |
+
"learning_rate": 9.999656469585957e-06,
|
226 |
+
"loss": 1.8743,
|
227 |
+
"step": 31
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.22614840989399293,
|
231 |
+
"grad_norm": 0.74609375,
|
232 |
+
"learning_rate": 9.999227067632223e-06,
|
233 |
+
"loss": 2.0273,
|
234 |
+
"step": 32
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.2332155477031802,
|
238 |
+
"grad_norm": 0.8359375,
|
239 |
+
"learning_rate": 9.99862592554908e-06,
|
240 |
+
"loss": 1.8072,
|
241 |
+
"step": 33
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.24028268551236748,
|
245 |
+
"grad_norm": 0.82421875,
|
246 |
+
"learning_rate": 9.997853063987768e-06,
|
247 |
+
"loss": 2.0589,
|
248 |
+
"step": 34
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.24734982332155478,
|
252 |
+
"grad_norm": 0.66796875,
|
253 |
+
"learning_rate": 9.996908509498662e-06,
|
254 |
+
"loss": 1.9282,
|
255 |
+
"step": 35
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.254416961130742,
|
259 |
+
"grad_norm": 1.046875,
|
260 |
+
"learning_rate": 9.995792294530356e-06,
|
261 |
+
"loss": 1.538,
|
262 |
+
"step": 36
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.26148409893992935,
|
266 |
+
"grad_norm": 0.81640625,
|
267 |
+
"learning_rate": 9.994504457428557e-06,
|
268 |
+
"loss": 1.9843,
|
269 |
+
"step": 37
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.26855123674911663,
|
273 |
+
"grad_norm": 1.84375,
|
274 |
+
"learning_rate": 9.993045042434772e-06,
|
275 |
+
"loss": 2.7539,
|
276 |
+
"step": 38
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.2756183745583039,
|
280 |
+
"grad_norm": 0.66796875,
|
281 |
+
"learning_rate": 9.99141409968477e-06,
|
282 |
+
"loss": 1.7211,
|
283 |
+
"step": 39
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.2826855123674912,
|
287 |
+
"grad_norm": 0.71875,
|
288 |
+
"learning_rate": 9.989611685206881e-06,
|
289 |
+
"loss": 2.1478,
|
290 |
+
"step": 40
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.28975265017667845,
|
294 |
+
"grad_norm": 0.65234375,
|
295 |
+
"learning_rate": 9.987637860920053e-06,
|
296 |
+
"loss": 2.0103,
|
297 |
+
"step": 41
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.2968197879858657,
|
301 |
+
"grad_norm": 0.63671875,
|
302 |
+
"learning_rate": 9.985492694631733e-06,
|
303 |
+
"loss": 1.4481,
|
304 |
+
"step": 42
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.303886925795053,
|
308 |
+
"grad_norm": 0.80078125,
|
309 |
+
"learning_rate": 9.983176260035546e-06,
|
310 |
+
"loss": 1.7512,
|
311 |
+
"step": 43
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.31095406360424027,
|
315 |
+
"grad_norm": 0.71875,
|
316 |
+
"learning_rate": 9.980688636708744e-06,
|
317 |
+
"loss": 2.061,
|
318 |
+
"step": 44
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.31802120141342755,
|
322 |
+
"grad_norm": 0.59765625,
|
323 |
+
"learning_rate": 9.978029910109491e-06,
|
324 |
+
"loss": 1.572,
|
325 |
+
"step": 45
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.3250883392226148,
|
329 |
+
"grad_norm": 0.66015625,
|
330 |
+
"learning_rate": 9.975200171573917e-06,
|
331 |
+
"loss": 2.0828,
|
332 |
+
"step": 46
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.3321554770318021,
|
336 |
+
"grad_norm": 0.63671875,
|
337 |
+
"learning_rate": 9.972199518312979e-06,
|
338 |
+
"loss": 1.8459,
|
339 |
+
"step": 47
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.3392226148409894,
|
343 |
+
"grad_norm": 0.6796875,
|
344 |
+
"learning_rate": 9.969028053409131e-06,
|
345 |
+
"loss": 2.2307,
|
346 |
+
"step": 48
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.3462897526501767,
|
350 |
+
"grad_norm": 0.65625,
|
351 |
+
"learning_rate": 9.965685885812773e-06,
|
352 |
+
"loss": 1.5793,
|
353 |
+
"step": 49
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.35335689045936397,
|
357 |
+
"grad_norm": 0.75,
|
358 |
+
"learning_rate": 9.96217313033851e-06,
|
359 |
+
"loss": 2.1297,
|
360 |
+
"step": 50
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.36042402826855124,
|
364 |
+
"grad_norm": 1.0625,
|
365 |
+
"learning_rate": 9.958489907661217e-06,
|
366 |
+
"loss": 1.912,
|
367 |
+
"step": 51
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.3674911660777385,
|
371 |
+
"grad_norm": 0.72265625,
|
372 |
+
"learning_rate": 9.95463634431188e-06,
|
373 |
+
"loss": 2.122,
|
374 |
+
"step": 52
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.3745583038869258,
|
378 |
+
"grad_norm": 0.59375,
|
379 |
+
"learning_rate": 9.950612572673255e-06,
|
380 |
+
"loss": 1.9928,
|
381 |
+
"step": 53
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.38162544169611307,
|
385 |
+
"grad_norm": 0.8984375,
|
386 |
+
"learning_rate": 9.946418730975326e-06,
|
387 |
+
"loss": 1.9401,
|
388 |
+
"step": 54
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.38869257950530034,
|
392 |
+
"grad_norm": 0.578125,
|
393 |
+
"learning_rate": 9.942054963290549e-06,
|
394 |
+
"loss": 1.742,
|
395 |
+
"step": 55
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.3957597173144876,
|
399 |
+
"grad_norm": 0.70703125,
|
400 |
+
"learning_rate": 9.9375214195289e-06,
|
401 |
+
"loss": 1.775,
|
402 |
+
"step": 56
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.4028268551236749,
|
406 |
+
"grad_norm": 0.64453125,
|
407 |
+
"learning_rate": 9.932818255432733e-06,
|
408 |
+
"loss": 1.9486,
|
409 |
+
"step": 57
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.4098939929328622,
|
413 |
+
"grad_norm": 0.7265625,
|
414 |
+
"learning_rate": 9.92794563257143e-06,
|
415 |
+
"loss": 1.7127,
|
416 |
+
"step": 58
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.4169611307420495,
|
420 |
+
"grad_norm": 0.66796875,
|
421 |
+
"learning_rate": 9.92290371833584e-06,
|
422 |
+
"loss": 2.1642,
|
423 |
+
"step": 59
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.42402826855123676,
|
427 |
+
"grad_norm": 0.83984375,
|
428 |
+
"learning_rate": 9.91769268593254e-06,
|
429 |
+
"loss": 1.7884,
|
430 |
+
"step": 60
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.43109540636042404,
|
434 |
+
"grad_norm": 0.68359375,
|
435 |
+
"learning_rate": 9.91231271437788e-06,
|
436 |
+
"loss": 2.1369,
|
437 |
+
"step": 61
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.4381625441696113,
|
441 |
+
"grad_norm": 0.75390625,
|
442 |
+
"learning_rate": 9.906763988491834e-06,
|
443 |
+
"loss": 2.2394,
|
444 |
+
"step": 62
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.4452296819787986,
|
448 |
+
"grad_norm": 0.5859375,
|
449 |
+
"learning_rate": 9.901046698891648e-06,
|
450 |
+
"loss": 1.4972,
|
451 |
+
"step": 63
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.45229681978798586,
|
455 |
+
"grad_norm": 0.96875,
|
456 |
+
"learning_rate": 9.895161041985295e-06,
|
457 |
+
"loss": 1.8555,
|
458 |
+
"step": 64
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.45936395759717313,
|
462 |
+
"grad_norm": 0.74609375,
|
463 |
+
"learning_rate": 9.889107219964726e-06,
|
464 |
+
"loss": 2.2285,
|
465 |
+
"step": 65
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.4664310954063604,
|
469 |
+
"grad_norm": 0.6015625,
|
470 |
+
"learning_rate": 9.882885440798928e-06,
|
471 |
+
"loss": 1.6138,
|
472 |
+
"step": 66
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.4734982332155477,
|
476 |
+
"grad_norm": 0.6171875,
|
477 |
+
"learning_rate": 9.876495918226772e-06,
|
478 |
+
"loss": 1.7915,
|
479 |
+
"step": 67
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.48056537102473496,
|
483 |
+
"grad_norm": 0.56640625,
|
484 |
+
"learning_rate": 9.869938871749676e-06,
|
485 |
+
"loss": 1.6075,
|
486 |
+
"step": 68
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.4876325088339223,
|
490 |
+
"grad_norm": 0.6640625,
|
491 |
+
"learning_rate": 9.863214526624065e-06,
|
492 |
+
"loss": 1.9207,
|
493 |
+
"step": 69
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.49469964664310956,
|
497 |
+
"grad_norm": 0.703125,
|
498 |
+
"learning_rate": 9.856323113853632e-06,
|
499 |
+
"loss": 1.9285,
|
500 |
+
"step": 70
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.5017667844522968,
|
504 |
+
"grad_norm": 0.68359375,
|
505 |
+
"learning_rate": 9.849264870181393e-06,
|
506 |
+
"loss": 1.9508,
|
507 |
+
"step": 71
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.508833922261484,
|
511 |
+
"grad_norm": 0.6640625,
|
512 |
+
"learning_rate": 9.842040038081572e-06,
|
513 |
+
"loss": 1.9983,
|
514 |
+
"step": 72
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.5159010600706714,
|
518 |
+
"grad_norm": 0.5703125,
|
519 |
+
"learning_rate": 9.834648865751254e-06,
|
520 |
+
"loss": 1.6503,
|
521 |
+
"step": 73
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.5229681978798587,
|
525 |
+
"grad_norm": 1.046875,
|
526 |
+
"learning_rate": 9.827091607101871e-06,
|
527 |
+
"loss": 1.8562,
|
528 |
+
"step": 74
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.5300353356890459,
|
532 |
+
"grad_norm": 0.78515625,
|
533 |
+
"learning_rate": 9.81936852175047e-06,
|
534 |
+
"loss": 1.5611,
|
535 |
+
"step": 75
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.5371024734982333,
|
539 |
+
"grad_norm": 0.61328125,
|
540 |
+
"learning_rate": 9.811479875010801e-06,
|
541 |
+
"loss": 1.7828,
|
542 |
+
"step": 76
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.5441696113074205,
|
546 |
+
"grad_norm": 0.6015625,
|
547 |
+
"learning_rate": 9.803425937884202e-06,
|
548 |
+
"loss": 1.5878,
|
549 |
+
"step": 77
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.5512367491166078,
|
553 |
+
"grad_norm": 0.76171875,
|
554 |
+
"learning_rate": 9.79520698705028e-06,
|
555 |
+
"loss": 2.0218,
|
556 |
+
"step": 78
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.558303886925795,
|
560 |
+
"grad_norm": 0.640625,
|
561 |
+
"learning_rate": 9.786823304857424e-06,
|
562 |
+
"loss": 1.4419,
|
563 |
+
"step": 79
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.5653710247349824,
|
567 |
+
"grad_norm": 1.2265625,
|
568 |
+
"learning_rate": 9.778275179313084e-06,
|
569 |
+
"loss": 1.9871,
|
570 |
+
"step": 80
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.5724381625441696,
|
574 |
+
"grad_norm": 0.71875,
|
575 |
+
"learning_rate": 9.769562904073896e-06,
|
576 |
+
"loss": 1.9268,
|
577 |
+
"step": 81
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.5795053003533569,
|
581 |
+
"grad_norm": 0.57421875,
|
582 |
+
"learning_rate": 9.76068677843558e-06,
|
583 |
+
"loss": 1.4848,
|
584 |
+
"step": 82
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.5865724381625441,
|
588 |
+
"grad_norm": 0.65234375,
|
589 |
+
"learning_rate": 9.751647107322668e-06,
|
590 |
+
"loss": 2.0959,
|
591 |
+
"step": 83
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.5936395759717314,
|
595 |
+
"grad_norm": 0.74609375,
|
596 |
+
"learning_rate": 9.742444201278022e-06,
|
597 |
+
"loss": 2.3728,
|
598 |
+
"step": 84
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.6007067137809188,
|
602 |
+
"grad_norm": 0.671875,
|
603 |
+
"learning_rate": 9.733078376452172e-06,
|
604 |
+
"loss": 1.3637,
|
605 |
+
"step": 85
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.607773851590106,
|
609 |
+
"grad_norm": 0.671875,
|
610 |
+
"learning_rate": 9.723549954592447e-06,
|
611 |
+
"loss": 1.8211,
|
612 |
+
"step": 86
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.6148409893992933,
|
616 |
+
"grad_norm": 0.64453125,
|
617 |
+
"learning_rate": 9.713859263031928e-06,
|
618 |
+
"loss": 1.9919,
|
619 |
+
"step": 87
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.6219081272084805,
|
623 |
+
"grad_norm": 0.6015625,
|
624 |
+
"learning_rate": 9.704006634678205e-06,
|
625 |
+
"loss": 1.5786,
|
626 |
+
"step": 88
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.6289752650176679,
|
630 |
+
"grad_norm": 0.6640625,
|
631 |
+
"learning_rate": 9.693992408001934e-06,
|
632 |
+
"loss": 1.9939,
|
633 |
+
"step": 89
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.6360424028268551,
|
637 |
+
"grad_norm": 0.60546875,
|
638 |
+
"learning_rate": 9.683816927025212e-06,
|
639 |
+
"loss": 2.1518,
|
640 |
+
"step": 90
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.6431095406360424,
|
644 |
+
"grad_norm": 0.7578125,
|
645 |
+
"learning_rate": 9.673480541309761e-06,
|
646 |
+
"loss": 2.2444,
|
647 |
+
"step": 91
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.6501766784452296,
|
651 |
+
"grad_norm": 0.609375,
|
652 |
+
"learning_rate": 9.662983605944918e-06,
|
653 |
+
"loss": 1.9037,
|
654 |
+
"step": 92
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.657243816254417,
|
658 |
+
"grad_norm": 1.5625,
|
659 |
+
"learning_rate": 9.652326481535434e-06,
|
660 |
+
"loss": 2.3459,
|
661 |
+
"step": 93
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.6643109540636042,
|
665 |
+
"grad_norm": 0.609375,
|
666 |
+
"learning_rate": 9.64150953418909e-06,
|
667 |
+
"loss": 1.7578,
|
668 |
+
"step": 94
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.6713780918727915,
|
672 |
+
"grad_norm": 0.6328125,
|
673 |
+
"learning_rate": 9.630533135504118e-06,
|
674 |
+
"loss": 1.5717,
|
675 |
+
"step": 95
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.6784452296819788,
|
679 |
+
"grad_norm": 0.7109375,
|
680 |
+
"learning_rate": 9.619397662556434e-06,
|
681 |
+
"loss": 1.7722,
|
682 |
+
"step": 96
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.6855123674911661,
|
686 |
+
"grad_norm": 0.6796875,
|
687 |
+
"learning_rate": 9.608103497886687e-06,
|
688 |
+
"loss": 1.8594,
|
689 |
+
"step": 97
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.6925795053003534,
|
693 |
+
"grad_norm": 0.66796875,
|
694 |
+
"learning_rate": 9.596651029487116e-06,
|
695 |
+
"loss": 2.1158,
|
696 |
+
"step": 98
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.6996466431095406,
|
700 |
+
"grad_norm": 0.75,
|
701 |
+
"learning_rate": 9.585040650788222e-06,
|
702 |
+
"loss": 1.2966,
|
703 |
+
"step": 99
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.7067137809187279,
|
707 |
+
"grad_norm": 1.2890625,
|
708 |
+
"learning_rate": 9.573272760645248e-06,
|
709 |
+
"loss": 2.3551,
|
710 |
+
"step": 100
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.7137809187279152,
|
714 |
+
"grad_norm": 0.61328125,
|
715 |
+
"learning_rate": 9.561347763324484e-06,
|
716 |
+
"loss": 2.0097,
|
717 |
+
"step": 101
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.7208480565371025,
|
721 |
+
"grad_norm": 0.6640625,
|
722 |
+
"learning_rate": 9.549266068489377e-06,
|
723 |
+
"loss": 1.7785,
|
724 |
+
"step": 102
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.7279151943462897,
|
728 |
+
"grad_norm": 0.59765625,
|
729 |
+
"learning_rate": 9.537028091186453e-06,
|
730 |
+
"loss": 1.7432,
|
731 |
+
"step": 103
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.734982332155477,
|
735 |
+
"grad_norm": 0.57421875,
|
736 |
+
"learning_rate": 9.524634251831064e-06,
|
737 |
+
"loss": 1.9585,
|
738 |
+
"step": 104
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.7420494699646644,
|
742 |
+
"grad_norm": 0.7890625,
|
743 |
+
"learning_rate": 9.512084976192944e-06,
|
744 |
+
"loss": 1.8571,
|
745 |
+
"step": 105
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.7491166077738516,
|
749 |
+
"grad_norm": 0.62890625,
|
750 |
+
"learning_rate": 9.499380695381577e-06,
|
751 |
+
"loss": 1.8799,
|
752 |
+
"step": 106
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.7561837455830389,
|
756 |
+
"grad_norm": 0.7421875,
|
757 |
+
"learning_rate": 9.486521845831403e-06,
|
758 |
+
"loss": 1.8795,
|
759 |
+
"step": 107
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.7632508833922261,
|
763 |
+
"grad_norm": 0.69140625,
|
764 |
+
"learning_rate": 9.4735088692868e-06,
|
765 |
+
"loss": 1.8043,
|
766 |
+
"step": 108
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.7703180212014135,
|
770 |
+
"grad_norm": 0.8125,
|
771 |
+
"learning_rate": 9.460342212786933e-06,
|
772 |
+
"loss": 2.1479,
|
773 |
+
"step": 109
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.7773851590106007,
|
777 |
+
"grad_norm": 0.7890625,
|
778 |
+
"learning_rate": 9.447022328650382e-06,
|
779 |
+
"loss": 1.7199,
|
780 |
+
"step": 110
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.784452296819788,
|
784 |
+
"grad_norm": 0.80078125,
|
785 |
+
"learning_rate": 9.43354967445961e-06,
|
786 |
+
"loss": 2.1058,
|
787 |
+
"step": 111
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.7915194346289752,
|
791 |
+
"grad_norm": 0.828125,
|
792 |
+
"learning_rate": 9.419924713045234e-06,
|
793 |
+
"loss": 1.9554,
|
794 |
+
"step": 112
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.7985865724381626,
|
798 |
+
"grad_norm": 0.64453125,
|
799 |
+
"learning_rate": 9.406147912470142e-06,
|
800 |
+
"loss": 1.3284,
|
801 |
+
"step": 113
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.8056537102473498,
|
805 |
+
"grad_norm": 0.66015625,
|
806 |
+
"learning_rate": 9.392219746013399e-06,
|
807 |
+
"loss": 1.8721,
|
808 |
+
"step": 114
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.8127208480565371,
|
812 |
+
"grad_norm": 0.5703125,
|
813 |
+
"learning_rate": 9.378140692153991e-06,
|
814 |
+
"loss": 1.8162,
|
815 |
+
"step": 115
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.8197879858657244,
|
819 |
+
"grad_norm": 0.6171875,
|
820 |
+
"learning_rate": 9.363911234554394e-06,
|
821 |
+
"loss": 2.1554,
|
822 |
+
"step": 116
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.8268551236749117,
|
826 |
+
"grad_norm": 0.703125,
|
827 |
+
"learning_rate": 9.349531862043952e-06,
|
828 |
+
"loss": 2.1176,
|
829 |
+
"step": 117
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.833922261484099,
|
833 |
+
"grad_norm": 0.609375,
|
834 |
+
"learning_rate": 9.335003068602087e-06,
|
835 |
+
"loss": 1.7494,
|
836 |
+
"step": 118
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.8409893992932862,
|
840 |
+
"grad_norm": 0.62109375,
|
841 |
+
"learning_rate": 9.320325353341325e-06,
|
842 |
+
"loss": 1.8479,
|
843 |
+
"step": 119
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.8480565371024735,
|
847 |
+
"grad_norm": 0.6328125,
|
848 |
+
"learning_rate": 9.305499220490162e-06,
|
849 |
+
"loss": 1.5816,
|
850 |
+
"step": 120
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.8551236749116607,
|
854 |
+
"grad_norm": 0.70703125,
|
855 |
+
"learning_rate": 9.290525179375722e-06,
|
856 |
+
"loss": 2.1121,
|
857 |
+
"step": 121
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.8621908127208481,
|
861 |
+
"grad_norm": 0.67578125,
|
862 |
+
"learning_rate": 9.275403744406282e-06,
|
863 |
+
"loss": 1.9516,
|
864 |
+
"step": 122
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.8692579505300353,
|
868 |
+
"grad_norm": 0.609375,
|
869 |
+
"learning_rate": 9.260135435053583e-06,
|
870 |
+
"loss": 1.8081,
|
871 |
+
"step": 123
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.8763250883392226,
|
875 |
+
"grad_norm": 0.62890625,
|
876 |
+
"learning_rate": 9.244720775834993e-06,
|
877 |
+
"loss": 2.2066,
|
878 |
+
"step": 124
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.8833922261484098,
|
882 |
+
"grad_norm": 0.80859375,
|
883 |
+
"learning_rate": 9.229160296295488e-06,
|
884 |
+
"loss": 2.0408,
|
885 |
+
"step": 125
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.8904593639575972,
|
889 |
+
"grad_norm": 0.6875,
|
890 |
+
"learning_rate": 9.213454530989454e-06,
|
891 |
+
"loss": 1.7211,
|
892 |
+
"step": 126
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.8975265017667845,
|
896 |
+
"grad_norm": 0.58984375,
|
897 |
+
"learning_rate": 9.197604019462334e-06,
|
898 |
+
"loss": 0.905,
|
899 |
+
"step": 127
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.9045936395759717,
|
903 |
+
"grad_norm": 0.65234375,
|
904 |
+
"learning_rate": 9.18160930623208e-06,
|
905 |
+
"loss": 1.4443,
|
906 |
+
"step": 128
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.911660777385159,
|
910 |
+
"grad_norm": 0.72265625,
|
911 |
+
"learning_rate": 9.165470940770458e-06,
|
912 |
+
"loss": 1.8498,
|
913 |
+
"step": 129
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.9187279151943463,
|
917 |
+
"grad_norm": 0.6875,
|
918 |
+
"learning_rate": 9.149189477484169e-06,
|
919 |
+
"loss": 1.7645,
|
920 |
+
"step": 130
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.9257950530035336,
|
924 |
+
"grad_norm": 0.59375,
|
925 |
+
"learning_rate": 9.132765475695795e-06,
|
926 |
+
"loss": 1.7509,
|
927 |
+
"step": 131
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.9328621908127208,
|
931 |
+
"grad_norm": 0.61328125,
|
932 |
+
"learning_rate": 9.116199499624596e-06,
|
933 |
+
"loss": 2.2509,
|
934 |
+
"step": 132
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.9399293286219081,
|
938 |
+
"grad_norm": 0.765625,
|
939 |
+
"learning_rate": 9.099492118367123e-06,
|
940 |
+
"loss": 1.5412,
|
941 |
+
"step": 133
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.9469964664310954,
|
945 |
+
"grad_norm": 0.609375,
|
946 |
+
"learning_rate": 9.082643905877665e-06,
|
947 |
+
"loss": 1.5065,
|
948 |
+
"step": 134
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.9540636042402827,
|
952 |
+
"grad_norm": 0.625,
|
953 |
+
"learning_rate": 9.065655440948536e-06,
|
954 |
+
"loss": 1.8347,
|
955 |
+
"step": 135
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.9611307420494699,
|
959 |
+
"grad_norm": 0.765625,
|
960 |
+
"learning_rate": 9.048527307190182e-06,
|
961 |
+
"loss": 2.1884,
|
962 |
+
"step": 136
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.9681978798586572,
|
966 |
+
"grad_norm": 0.62109375,
|
967 |
+
"learning_rate": 9.03126009301115e-06,
|
968 |
+
"loss": 1.7727,
|
969 |
+
"step": 137
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.9752650176678446,
|
973 |
+
"grad_norm": 0.61328125,
|
974 |
+
"learning_rate": 9.013854391597856e-06,
|
975 |
+
"loss": 1.7151,
|
976 |
+
"step": 138
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.9823321554770318,
|
980 |
+
"grad_norm": 0.66796875,
|
981 |
+
"learning_rate": 8.996310800894215e-06,
|
982 |
+
"loss": 1.992,
|
983 |
+
"step": 139
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.9893992932862191,
|
987 |
+
"grad_norm": 0.69140625,
|
988 |
+
"learning_rate": 8.978629923581104e-06,
|
989 |
+
"loss": 2.2281,
|
990 |
+
"step": 140
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.9964664310954063,
|
994 |
+
"grad_norm": 1.15625,
|
995 |
+
"learning_rate": 8.960812367055646e-06,
|
996 |
+
"loss": 2.874,
|
997 |
+
"step": 141
|
998 |
+
}
|
999 |
+
],
|
1000 |
+
"logging_steps": 1,
|
1001 |
+
"max_steps": 564,
|
1002 |
+
"num_input_tokens_seen": 0,
|
1003 |
+
"num_train_epochs": 4,
|
1004 |
+
"save_steps": 141,
|
1005 |
+
"stateful_callbacks": {
|
1006 |
+
"TrainerControl": {
|
1007 |
+
"args": {
|
1008 |
+
"should_epoch_stop": false,
|
1009 |
+
"should_evaluate": false,
|
1010 |
+
"should_log": false,
|
1011 |
+
"should_save": true,
|
1012 |
+
"should_training_stop": false
|
1013 |
+
},
|
1014 |
+
"attributes": {}
|
1015 |
+
}
|
1016 |
+
},
|
1017 |
+
"total_flos": 4.4279482344800256e+17,
|
1018 |
+
"train_batch_size": 2,
|
1019 |
+
"trial_name": null,
|
1020 |
+
"trial_params": null
|
1021 |
+
}
|
checkpoint-141/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:406982d99a22da9752c26535cc9f5894b29792d701bc3fe309a0db5d133444df
|
3 |
+
size 6840
|
checkpoint-141/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|