Jonathanmann commited on
Commit
4a33c9a
·
verified ·
1 Parent(s): 88ff898

Upload 15 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: cc-by-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29dee68a2d501bf6688ccb135a6e5b42acfe44432b85b7358ff9036f6cdef27c
3
+ size 6824216
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 128256,
3
+ "max_position_embeddings": 131072,
4
+ "hidden_size": 2048,
5
+ "intermediate_size": 8192,
6
+ "num_hidden_layers": 16,
7
+ "num_attention_heads": 32,
8
+ "num_key_value_heads": 8,
9
+ "hidden_act": "silu",
10
+ "initializer_range": 0.02,
11
+ "rms_norm_eps": 1e-05,
12
+ "pretraining_tp": 1,
13
+ "use_cache": true,
14
+ "rope_theta": 500000.0,
15
+ "rope_scaling": {
16
+ "factor": 32.0,
17
+ "high_freq_factor": 4.0,
18
+ "low_freq_factor": 1.0,
19
+ "original_max_position_embeddings": 8192,
20
+ "rope_type": "llama3"
21
+ },
22
+ "attention_bias": false,
23
+ "attention_dropout": 0.0,
24
+ "mlp_bias": false,
25
+ "head_dim": 64,
26
+ "return_dict": true,
27
+ "output_hidden_states": false,
28
+ "output_attentions": false,
29
+ "torchscript": false,
30
+ "torch_dtype": "float16",
31
+ "use_bfloat16": false,
32
+ "tf_legacy_loss": false,
33
+ "pruned_heads": {},
34
+ "tie_word_embeddings": true,
35
+ "chunk_size_feed_forward": 0,
36
+ "is_encoder_decoder": false,
37
+ "is_decoder": false,
38
+ "cross_attention_hidden_size": null,
39
+ "add_cross_attention": false,
40
+ "tie_encoder_decoder": false,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "do_sample": false,
44
+ "early_stopping": false,
45
+ "num_beams": 1,
46
+ "num_beam_groups": 1,
47
+ "diversity_penalty": 0.0,
48
+ "temperature": 1.0,
49
+ "top_k": 50,
50
+ "top_p": 1.0,
51
+ "typical_p": 1.0,
52
+ "repetition_penalty": 1.0,
53
+ "length_penalty": 1.0,
54
+ "no_repeat_ngram_size": 0,
55
+ "encoder_no_repeat_ngram_size": 0,
56
+ "bad_words_ids": null,
57
+ "num_return_sequences": 1,
58
+ "output_scores": false,
59
+ "return_dict_in_generate": false,
60
+ "forced_bos_token_id": null,
61
+ "forced_eos_token_id": null,
62
+ "remove_invalid_values": false,
63
+ "exponential_decay_length_penalty": null,
64
+ "suppress_tokens": null,
65
+ "begin_suppress_tokens": null,
66
+ "architectures": [
67
+ "LlamaForCausalLM"
68
+ ],
69
+ "finetuning_task": null,
70
+ "id2label": {
71
+ "0": "LABEL_0",
72
+ "1": "LABEL_1"
73
+ },
74
+ "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1
77
+ },
78
+ "tokenizer_class": null,
79
+ "prefix": null,
80
+ "bos_token_id": 128000,
81
+ "pad_token_id": null,
82
+ "eos_token_id": [
83
+ 128001,
84
+ 128008,
85
+ 128009
86
+ ],
87
+ "sep_token_id": null,
88
+ "decoder_start_token_id": null,
89
+ "task_specific_params": null,
90
+ "problem_type": null,
91
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
92
+ "_attn_implementation_autoset": true,
93
+ "transformers_version": "4.46.3",
94
+ "model_type": "llama"
95
+ }
lora_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "peft_type": "LORA",
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "revision": null,
6
+ "task_type": "CAUSAL_LM",
7
+ "inference_mode": false,
8
+ "r": 16,
9
+ "target_modules": "{'q_proj', 'v_proj'}",
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "fan_in_fan_out": false,
13
+ "bias": "none",
14
+ "use_rslora": false,
15
+ "modules_to_save": null,
16
+ "init_lora_weights": true,
17
+ "layers_to_transform": null,
18
+ "layers_pattern": null,
19
+ "rank_pattern": {},
20
+ "alpha_pattern": {},
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "loftq_config": {},
24
+ "use_dora": false,
25
+ "layer_replication": null
26
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa16bcfe1f136b2d02b14a49690bbb21d3c0af4f1a47277a72cb9b6e25ccf77
3
+ size 13685562
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de27dcbe8d73ffe225e427ebd2690ba439c4fdb28e8252a23d660d5edb1f55f
3
+ size 14308
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8308f8e85d2638368130e04cae1729eac9a2b34a301e436944485284d9a28a
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
tokenizer_full_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_max_length": 131072,
3
+ "padding_side": "right",
4
+ "pad_token": "<|eot_id|>",
5
+ "eos_token": "<|eot_id|>",
6
+ "name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
7
+ "tokenizer_class": "PreTrainedTokenizerFast",
8
+ "special_tokens": {
9
+ "bos_token": "<|begin_of_text|>",
10
+ "eos_token": "<|eot_id|>",
11
+ "pad_token": "<|eot_id|>"
12
+ }
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,1670 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5767922401428223,
3
+ "best_model_checkpoint": "/content/drive/My Drive/Hugh Mann/Llama3.2-1B-instruct-SMS-Young/checkpoint-1000",
4
+ "epoch": 0.9998703487618307,
5
+ "global_step": 1928,
6
+ "log_history": [
7
+ {
8
+ "loss": 4.5223,
9
+ "grad_norm": 2.790254592895508,
10
+ "learning_rate": 5.000000000000001e-07,
11
+ "epoch": 0.005186049526772981,
12
+ "step": 10
13
+ },
14
+ {
15
+ "loss": 4.52,
16
+ "grad_norm": 2.8902390003204346,
17
+ "learning_rate": 1.0000000000000002e-06,
18
+ "epoch": 0.010372099053545962,
19
+ "step": 20
20
+ },
21
+ {
22
+ "loss": 4.5975,
23
+ "grad_norm": 2.8794925212860107,
24
+ "learning_rate": 1.5e-06,
25
+ "epoch": 0.015558148580318941,
26
+ "step": 30
27
+ },
28
+ {
29
+ "loss": 4.5163,
30
+ "grad_norm": 3.1455466747283936,
31
+ "learning_rate": 2.0000000000000003e-06,
32
+ "epoch": 0.020744198107091924,
33
+ "step": 40
34
+ },
35
+ {
36
+ "loss": 4.5436,
37
+ "grad_norm": 2.8355510234832764,
38
+ "learning_rate": 2.5e-06,
39
+ "epoch": 0.025930247633864905,
40
+ "step": 50
41
+ },
42
+ {
43
+ "eval_loss": 4.624587535858154,
44
+ "eval_runtime": 85.8201,
45
+ "eval_samples_per_second": 79.888,
46
+ "eval_steps_per_second": 9.986,
47
+ "epoch": 0.025930247633864905,
48
+ "step": 50
49
+ },
50
+ {
51
+ "loss": 4.5336,
52
+ "grad_norm": 3.0655930042266846,
53
+ "learning_rate": 3e-06,
54
+ "epoch": 0.031116297160637883,
55
+ "step": 60
56
+ },
57
+ {
58
+ "loss": 4.4666,
59
+ "grad_norm": 3.1291167736053467,
60
+ "learning_rate": 3.5e-06,
61
+ "epoch": 0.036302346687410864,
62
+ "step": 70
63
+ },
64
+ {
65
+ "loss": 4.4154,
66
+ "grad_norm": 2.9255363941192627,
67
+ "learning_rate": 4.000000000000001e-06,
68
+ "epoch": 0.04148839621418385,
69
+ "step": 80
70
+ },
71
+ {
72
+ "loss": 4.4187,
73
+ "grad_norm": 2.990316390991211,
74
+ "learning_rate": 4.5e-06,
75
+ "epoch": 0.046674445740956826,
76
+ "step": 90
77
+ },
78
+ {
79
+ "loss": 4.3335,
80
+ "grad_norm": 3.100736379623413,
81
+ "learning_rate": 5e-06,
82
+ "epoch": 0.05186049526772981,
83
+ "step": 100
84
+ },
85
+ {
86
+ "eval_loss": 4.384247303009033,
87
+ "eval_runtime": 85.9003,
88
+ "eval_samples_per_second": 79.813,
89
+ "eval_steps_per_second": 9.977,
90
+ "epoch": 0.05186049526772981,
91
+ "step": 100
92
+ },
93
+ {
94
+ "loss": 4.2383,
95
+ "grad_norm": 3.111485719680786,
96
+ "learning_rate": 5.500000000000001e-06,
97
+ "epoch": 0.05704654479450279,
98
+ "step": 110
99
+ },
100
+ {
101
+ "loss": 4.2089,
102
+ "grad_norm": 3.3347222805023193,
103
+ "learning_rate": 6e-06,
104
+ "epoch": 0.062232594321275765,
105
+ "step": 120
106
+ },
107
+ {
108
+ "loss": 4.1144,
109
+ "grad_norm": 3.123852491378784,
110
+ "learning_rate": 6.5000000000000004e-06,
111
+ "epoch": 0.06741864384804874,
112
+ "step": 130
113
+ },
114
+ {
115
+ "loss": 3.9817,
116
+ "grad_norm": 3.168285846710205,
117
+ "learning_rate": 7e-06,
118
+ "epoch": 0.07260469337482173,
119
+ "step": 140
120
+ },
121
+ {
122
+ "loss": 3.8978,
123
+ "grad_norm": 2.250338315963745,
124
+ "learning_rate": 7.500000000000001e-06,
125
+ "epoch": 0.07779074290159471,
126
+ "step": 150
127
+ },
128
+ {
129
+ "eval_loss": 3.874814510345459,
130
+ "eval_runtime": 85.9688,
131
+ "eval_samples_per_second": 79.75,
132
+ "eval_steps_per_second": 9.969,
133
+ "epoch": 0.07779074290159471,
134
+ "step": 150
135
+ },
136
+ {
137
+ "loss": 3.7348,
138
+ "grad_norm": 2.712542772293091,
139
+ "learning_rate": 8.000000000000001e-06,
140
+ "epoch": 0.0829767924283677,
141
+ "step": 160
142
+ },
143
+ {
144
+ "loss": 3.5919,
145
+ "grad_norm": 2.9881999492645264,
146
+ "learning_rate": 8.5e-06,
147
+ "epoch": 0.08816284195514067,
148
+ "step": 170
149
+ },
150
+ {
151
+ "loss": 3.4981,
152
+ "grad_norm": 2.8425819873809814,
153
+ "learning_rate": 9e-06,
154
+ "epoch": 0.09334889148191365,
155
+ "step": 180
156
+ },
157
+ {
158
+ "loss": 3.3046,
159
+ "grad_norm": 2.8154757022857666,
160
+ "learning_rate": 9.5e-06,
161
+ "epoch": 0.09853494100868664,
162
+ "step": 190
163
+ },
164
+ {
165
+ "loss": 3.1184,
166
+ "grad_norm": 3.20194149017334,
167
+ "learning_rate": 1e-05,
168
+ "epoch": 0.10372099053545962,
169
+ "step": 200
170
+ },
171
+ {
172
+ "eval_loss": 3.069911479949951,
173
+ "eval_runtime": 85.9453,
174
+ "eval_samples_per_second": 79.772,
175
+ "eval_steps_per_second": 9.971,
176
+ "epoch": 0.10372099053545962,
177
+ "step": 200
178
+ },
179
+ {
180
+ "loss": 2.9355,
181
+ "grad_norm": 3.575906753540039,
182
+ "learning_rate": 9.942129629629629e-06,
183
+ "epoch": 0.10890704006223259,
184
+ "step": 210
185
+ },
186
+ {
187
+ "loss": 2.6817,
188
+ "grad_norm": 4.213418960571289,
189
+ "learning_rate": 9.88425925925926e-06,
190
+ "epoch": 0.11409308958900558,
191
+ "step": 220
192
+ },
193
+ {
194
+ "loss": 2.4779,
195
+ "grad_norm": 4.348301410675049,
196
+ "learning_rate": 9.826388888888889e-06,
197
+ "epoch": 0.11927913911577856,
198
+ "step": 230
199
+ },
200
+ {
201
+ "loss": 2.1924,
202
+ "grad_norm": 4.169698715209961,
203
+ "learning_rate": 9.768518518518519e-06,
204
+ "epoch": 0.12446518864255153,
205
+ "step": 240
206
+ },
207
+ {
208
+ "loss": 2.1011,
209
+ "grad_norm": 2.842150926589966,
210
+ "learning_rate": 9.710648148148149e-06,
211
+ "epoch": 0.12965123816932453,
212
+ "step": 250
213
+ },
214
+ {
215
+ "eval_loss": 1.9660704135894775,
216
+ "eval_runtime": 86.4563,
217
+ "eval_samples_per_second": 79.3,
218
+ "eval_steps_per_second": 9.913,
219
+ "epoch": 0.12965123816932453,
220
+ "step": 250
221
+ },
222
+ {
223
+ "loss": 1.8366,
224
+ "grad_norm": 1.8788377046585083,
225
+ "learning_rate": 9.652777777777779e-06,
226
+ "epoch": 0.13483728769609749,
227
+ "step": 260
228
+ },
229
+ {
230
+ "loss": 1.8616,
231
+ "grad_norm": 1.0984115600585938,
232
+ "learning_rate": 9.594907407407407e-06,
233
+ "epoch": 0.14002333722287047,
234
+ "step": 270
235
+ },
236
+ {
237
+ "loss": 1.7217,
238
+ "grad_norm": 0.9817687273025513,
239
+ "learning_rate": 9.537037037037037e-06,
240
+ "epoch": 0.14520938674964345,
241
+ "step": 280
242
+ },
243
+ {
244
+ "loss": 1.7435,
245
+ "grad_norm": 0.894806444644928,
246
+ "learning_rate": 9.479166666666667e-06,
247
+ "epoch": 0.15039543627641644,
248
+ "step": 290
249
+ },
250
+ {
251
+ "loss": 1.7994,
252
+ "grad_norm": 0.8035613298416138,
253
+ "learning_rate": 9.421296296296297e-06,
254
+ "epoch": 0.15558148580318942,
255
+ "step": 300
256
+ },
257
+ {
258
+ "eval_loss": 1.7215873003005981,
259
+ "eval_runtime": 86.3782,
260
+ "eval_samples_per_second": 79.372,
261
+ "eval_steps_per_second": 9.921,
262
+ "epoch": 0.15558148580318942,
263
+ "step": 300
264
+ },
265
+ {
266
+ "loss": 1.7297,
267
+ "grad_norm": 0.8026513457298279,
268
+ "learning_rate": 9.363425925925927e-06,
269
+ "epoch": 0.1607675353299624,
270
+ "step": 310
271
+ },
272
+ {
273
+ "loss": 1.6883,
274
+ "grad_norm": 0.722503662109375,
275
+ "learning_rate": 9.305555555555557e-06,
276
+ "epoch": 0.1659535848567354,
277
+ "step": 320
278
+ },
279
+ {
280
+ "loss": 1.7489,
281
+ "grad_norm": 0.7093557119369507,
282
+ "learning_rate": 9.247685185185185e-06,
283
+ "epoch": 0.17113963438350835,
284
+ "step": 330
285
+ },
286
+ {
287
+ "loss": 1.7492,
288
+ "grad_norm": 0.8062456846237183,
289
+ "learning_rate": 9.189814814814815e-06,
290
+ "epoch": 0.17632568391028133,
291
+ "step": 340
292
+ },
293
+ {
294
+ "loss": 1.7821,
295
+ "grad_norm": 0.8049404621124268,
296
+ "learning_rate": 9.131944444444445e-06,
297
+ "epoch": 0.18151173343705432,
298
+ "step": 350
299
+ },
300
+ {
301
+ "eval_loss": 1.676695704460144,
302
+ "eval_runtime": 86.1891,
303
+ "eval_samples_per_second": 79.546,
304
+ "eval_steps_per_second": 9.943,
305
+ "epoch": 0.18151173343705432,
306
+ "step": 350
307
+ },
308
+ {
309
+ "loss": 1.6539,
310
+ "grad_norm": 0.9094014167785645,
311
+ "learning_rate": 9.074074074074075e-06,
312
+ "epoch": 0.1866977829638273,
313
+ "step": 360
314
+ },
315
+ {
316
+ "loss": 1.7585,
317
+ "grad_norm": 0.6639271378517151,
318
+ "learning_rate": 9.016203703703704e-06,
319
+ "epoch": 0.1918838324906003,
320
+ "step": 370
321
+ },
322
+ {
323
+ "loss": 1.6665,
324
+ "grad_norm": 0.8052814602851868,
325
+ "learning_rate": 8.958333333333334e-06,
326
+ "epoch": 0.19706988201737327,
327
+ "step": 380
328
+ },
329
+ {
330
+ "loss": 1.7093,
331
+ "grad_norm": 0.8642238974571228,
332
+ "learning_rate": 8.900462962962964e-06,
333
+ "epoch": 0.20225593154414626,
334
+ "step": 390
335
+ },
336
+ {
337
+ "loss": 1.7105,
338
+ "grad_norm": 0.8282484412193298,
339
+ "learning_rate": 8.842592592592594e-06,
340
+ "epoch": 0.20744198107091924,
341
+ "step": 400
342
+ },
343
+ {
344
+ "eval_loss": 1.6555745601654053,
345
+ "eval_runtime": 86.2604,
346
+ "eval_samples_per_second": 79.48,
347
+ "eval_steps_per_second": 9.935,
348
+ "epoch": 0.20744198107091924,
349
+ "step": 400
350
+ },
351
+ {
352
+ "loss": 1.605,
353
+ "grad_norm": 0.7959835529327393,
354
+ "learning_rate": 8.784722222222224e-06,
355
+ "epoch": 0.2126280305976922,
356
+ "step": 410
357
+ },
358
+ {
359
+ "loss": 1.5952,
360
+ "grad_norm": 0.8222413659095764,
361
+ "learning_rate": 8.726851851851854e-06,
362
+ "epoch": 0.21781408012446518,
363
+ "step": 420
364
+ },
365
+ {
366
+ "loss": 1.6479,
367
+ "grad_norm": 0.9472383260726929,
368
+ "learning_rate": 8.668981481481482e-06,
369
+ "epoch": 0.22300012965123817,
370
+ "step": 430
371
+ },
372
+ {
373
+ "loss": 1.7536,
374
+ "grad_norm": 0.9353771209716797,
375
+ "learning_rate": 8.611111111111112e-06,
376
+ "epoch": 0.22818617917801115,
377
+ "step": 440
378
+ },
379
+ {
380
+ "loss": 1.5931,
381
+ "grad_norm": 0.73890620470047,
382
+ "learning_rate": 8.553240740740742e-06,
383
+ "epoch": 0.23337222870478413,
384
+ "step": 450
385
+ },
386
+ {
387
+ "eval_loss": 1.6408356428146362,
388
+ "eval_runtime": 86.2407,
389
+ "eval_samples_per_second": 79.498,
390
+ "eval_steps_per_second": 9.937,
391
+ "epoch": 0.23337222870478413,
392
+ "step": 450
393
+ },
394
+ {
395
+ "loss": 1.6429,
396
+ "grad_norm": 0.7909255027770996,
397
+ "learning_rate": 8.495370370370372e-06,
398
+ "epoch": 0.23855827823155712,
399
+ "step": 460
400
+ },
401
+ {
402
+ "loss": 1.6348,
403
+ "grad_norm": 0.753886878490448,
404
+ "learning_rate": 8.4375e-06,
405
+ "epoch": 0.2437443277583301,
406
+ "step": 470
407
+ },
408
+ {
409
+ "loss": 1.6181,
410
+ "grad_norm": 0.8351048231124878,
411
+ "learning_rate": 8.37962962962963e-06,
412
+ "epoch": 0.24893037728510306,
413
+ "step": 480
414
+ },
415
+ {
416
+ "loss": 1.5701,
417
+ "grad_norm": 1.116701602935791,
418
+ "learning_rate": 8.32175925925926e-06,
419
+ "epoch": 0.2541164268118761,
420
+ "step": 490
421
+ },
422
+ {
423
+ "loss": 1.6566,
424
+ "grad_norm": 0.7918911576271057,
425
+ "learning_rate": 8.263888888888888e-06,
426
+ "epoch": 0.25930247633864906,
427
+ "step": 500
428
+ },
429
+ {
430
+ "eval_loss": 1.6282782554626465,
431
+ "eval_runtime": 86.2204,
432
+ "eval_samples_per_second": 79.517,
433
+ "eval_steps_per_second": 9.94,
434
+ "epoch": 0.25930247633864906,
435
+ "step": 500
436
+ },
437
+ {
438
+ "loss": 1.5708,
439
+ "grad_norm": 0.800946831703186,
440
+ "learning_rate": 8.20601851851852e-06,
441
+ "epoch": 0.26448852586542204,
442
+ "step": 510
443
+ },
444
+ {
445
+ "loss": 1.5745,
446
+ "grad_norm": 0.8413161635398865,
447
+ "learning_rate": 8.148148148148148e-06,
448
+ "epoch": 0.26967457539219497,
449
+ "step": 520
450
+ },
451
+ {
452
+ "loss": 1.6055,
453
+ "grad_norm": 0.8265829682350159,
454
+ "learning_rate": 8.090277777777778e-06,
455
+ "epoch": 0.27486062491896796,
456
+ "step": 530
457
+ },
458
+ {
459
+ "loss": 1.5644,
460
+ "grad_norm": 0.8762720823287964,
461
+ "learning_rate": 8.032407407407408e-06,
462
+ "epoch": 0.28004667444574094,
463
+ "step": 540
464
+ },
465
+ {
466
+ "loss": 1.6221,
467
+ "grad_norm": 0.9819937944412231,
468
+ "learning_rate": 7.974537037037038e-06,
469
+ "epoch": 0.2852327239725139,
470
+ "step": 550
471
+ },
472
+ {
473
+ "eval_loss": 1.6173746585845947,
474
+ "eval_runtime": 86.0487,
475
+ "eval_samples_per_second": 79.676,
476
+ "eval_steps_per_second": 9.959,
477
+ "epoch": 0.2852327239725139,
478
+ "step": 550
479
+ },
480
+ {
481
+ "loss": 1.6147,
482
+ "grad_norm": 0.7989621758460999,
483
+ "learning_rate": 7.916666666666667e-06,
484
+ "epoch": 0.2904187734992869,
485
+ "step": 560
486
+ },
487
+ {
488
+ "loss": 1.6469,
489
+ "grad_norm": 0.7633054852485657,
490
+ "learning_rate": 7.858796296296297e-06,
491
+ "epoch": 0.2956048230260599,
492
+ "step": 570
493
+ },
494
+ {
495
+ "loss": 1.6038,
496
+ "grad_norm": 0.7922123074531555,
497
+ "learning_rate": 7.800925925925926e-06,
498
+ "epoch": 0.3007908725528329,
499
+ "step": 580
500
+ },
501
+ {
502
+ "loss": 1.6663,
503
+ "grad_norm": 0.8797257542610168,
504
+ "learning_rate": 7.743055555555556e-06,
505
+ "epoch": 0.30597692207960586,
506
+ "step": 590
507
+ },
508
+ {
509
+ "loss": 1.6022,
510
+ "grad_norm": 0.8298176527023315,
511
+ "learning_rate": 7.685185185185185e-06,
512
+ "epoch": 0.31116297160637885,
513
+ "step": 600
514
+ },
515
+ {
516
+ "eval_loss": 1.6079224348068237,
517
+ "eval_runtime": 86.1492,
518
+ "eval_samples_per_second": 79.583,
519
+ "eval_steps_per_second": 9.948,
520
+ "epoch": 0.31116297160637885,
521
+ "step": 600
522
+ },
523
+ {
524
+ "loss": 1.6263,
525
+ "grad_norm": 0.7946900725364685,
526
+ "learning_rate": 7.627314814814816e-06,
527
+ "epoch": 0.31634902113315183,
528
+ "step": 610
529
+ },
530
+ {
531
+ "loss": 1.5948,
532
+ "grad_norm": 0.9033863544464111,
533
+ "learning_rate": 7.569444444444445e-06,
534
+ "epoch": 0.3215350706599248,
535
+ "step": 620
536
+ },
537
+ {
538
+ "loss": 1.6061,
539
+ "grad_norm": 0.894698441028595,
540
+ "learning_rate": 7.511574074074075e-06,
541
+ "epoch": 0.3267211201866978,
542
+ "step": 630
543
+ },
544
+ {
545
+ "loss": 1.5519,
546
+ "grad_norm": 0.9097292423248291,
547
+ "learning_rate": 7.453703703703704e-06,
548
+ "epoch": 0.3319071697134708,
549
+ "step": 640
550
+ },
551
+ {
552
+ "loss": 1.5079,
553
+ "grad_norm": 1.0246304273605347,
554
+ "learning_rate": 7.395833333333335e-06,
555
+ "epoch": 0.33709321924024377,
556
+ "step": 650
557
+ },
558
+ {
559
+ "eval_loss": 1.6009989976882935,
560
+ "eval_runtime": 86.1362,
561
+ "eval_samples_per_second": 79.595,
562
+ "eval_steps_per_second": 9.949,
563
+ "epoch": 0.33709321924024377,
564
+ "step": 650
565
+ },
566
+ {
567
+ "loss": 1.6233,
568
+ "grad_norm": 0.9714149832725525,
569
+ "learning_rate": 7.337962962962964e-06,
570
+ "epoch": 0.3422792687670167,
571
+ "step": 660
572
+ },
573
+ {
574
+ "loss": 1.6339,
575
+ "grad_norm": 0.8516764640808105,
576
+ "learning_rate": 7.280092592592594e-06,
577
+ "epoch": 0.3474653182937897,
578
+ "step": 670
579
+ },
580
+ {
581
+ "loss": 1.541,
582
+ "grad_norm": 0.853626012802124,
583
+ "learning_rate": 7.222222222222223e-06,
584
+ "epoch": 0.35265136782056267,
585
+ "step": 680
586
+ },
587
+ {
588
+ "loss": 1.6094,
589
+ "grad_norm": 1.0543837547302246,
590
+ "learning_rate": 7.164351851851853e-06,
591
+ "epoch": 0.35783741734733565,
592
+ "step": 690
593
+ },
594
+ {
595
+ "loss": 1.5773,
596
+ "grad_norm": 0.8150729537010193,
597
+ "learning_rate": 7.106481481481482e-06,
598
+ "epoch": 0.36302346687410864,
599
+ "step": 700
600
+ },
601
+ {
602
+ "eval_loss": 1.5953495502471924,
603
+ "eval_runtime": 86.1632,
604
+ "eval_samples_per_second": 79.57,
605
+ "eval_steps_per_second": 9.946,
606
+ "epoch": 0.36302346687410864,
607
+ "step": 700
608
+ },
609
+ {
610
+ "loss": 1.5914,
611
+ "grad_norm": 0.9600136280059814,
612
+ "learning_rate": 7.048611111111112e-06,
613
+ "epoch": 0.3682095164008816,
614
+ "step": 710
615
+ },
616
+ {
617
+ "loss": 1.5879,
618
+ "grad_norm": 1.0759202241897583,
619
+ "learning_rate": 6.990740740740741e-06,
620
+ "epoch": 0.3733955659276546,
621
+ "step": 720
622
+ },
623
+ {
624
+ "loss": 1.5895,
625
+ "grad_norm": 0.8327440023422241,
626
+ "learning_rate": 6.932870370370371e-06,
627
+ "epoch": 0.3785816154544276,
628
+ "step": 730
629
+ },
630
+ {
631
+ "loss": 1.6505,
632
+ "grad_norm": 1.0032063722610474,
633
+ "learning_rate": 6.875e-06,
634
+ "epoch": 0.3837676649812006,
635
+ "step": 740
636
+ },
637
+ {
638
+ "loss": 1.5786,
639
+ "grad_norm": 0.9516606330871582,
640
+ "learning_rate": 6.817129629629629e-06,
641
+ "epoch": 0.38895371450797356,
642
+ "step": 750
643
+ },
644
+ {
645
+ "eval_loss": 1.5913790464401245,
646
+ "eval_runtime": 86.445,
647
+ "eval_samples_per_second": 79.311,
648
+ "eval_steps_per_second": 9.914,
649
+ "epoch": 0.38895371450797356,
650
+ "step": 750
651
+ },
652
+ {
653
+ "loss": 1.6009,
654
+ "grad_norm": 0.8432859778404236,
655
+ "learning_rate": 6.75925925925926e-06,
656
+ "epoch": 0.39413976403474654,
657
+ "step": 760
658
+ },
659
+ {
660
+ "loss": 1.5865,
661
+ "grad_norm": 0.8782029747962952,
662
+ "learning_rate": 6.701388888888889e-06,
663
+ "epoch": 0.3993258135615195,
664
+ "step": 770
665
+ },
666
+ {
667
+ "loss": 1.5593,
668
+ "grad_norm": 0.9644037485122681,
669
+ "learning_rate": 6.643518518518519e-06,
670
+ "epoch": 0.4045118630882925,
671
+ "step": 780
672
+ },
673
+ {
674
+ "loss": 1.5363,
675
+ "grad_norm": 0.8326228857040405,
676
+ "learning_rate": 6.5856481481481484e-06,
677
+ "epoch": 0.4096979126150655,
678
+ "step": 790
679
+ },
680
+ {
681
+ "loss": 1.6159,
682
+ "grad_norm": 1.0446785688400269,
683
+ "learning_rate": 6.5277777777777784e-06,
684
+ "epoch": 0.4148839621418385,
685
+ "step": 800
686
+ },
687
+ {
688
+ "eval_loss": 1.5873260498046875,
689
+ "eval_runtime": 86.4921,
690
+ "eval_samples_per_second": 79.267,
691
+ "eval_steps_per_second": 9.908,
692
+ "epoch": 0.4148839621418385,
693
+ "step": 800
694
+ },
695
+ {
696
+ "loss": 1.5581,
697
+ "grad_norm": 0.8821725249290466,
698
+ "learning_rate": 6.4699074074074076e-06,
699
+ "epoch": 0.4200700116686114,
700
+ "step": 810
701
+ },
702
+ {
703
+ "loss": 1.5431,
704
+ "grad_norm": 0.8592581152915955,
705
+ "learning_rate": 6.4120370370370375e-06,
706
+ "epoch": 0.4252560611953844,
707
+ "step": 820
708
+ },
709
+ {
710
+ "loss": 1.5795,
711
+ "grad_norm": 0.9633499383926392,
712
+ "learning_rate": 6.354166666666667e-06,
713
+ "epoch": 0.4304421107221574,
714
+ "step": 830
715
+ },
716
+ {
717
+ "loss": 1.5097,
718
+ "grad_norm": 0.934374213218689,
719
+ "learning_rate": 6.296296296296297e-06,
720
+ "epoch": 0.43562816024893036,
721
+ "step": 840
722
+ },
723
+ {
724
+ "loss": 1.5755,
725
+ "grad_norm": 1.0885519981384277,
726
+ "learning_rate": 6.238425925925926e-06,
727
+ "epoch": 0.44081420977570335,
728
+ "step": 850
729
+ },
730
+ {
731
+ "eval_loss": 1.5838837623596191,
732
+ "eval_runtime": 86.4732,
733
+ "eval_samples_per_second": 79.285,
734
+ "eval_steps_per_second": 9.911,
735
+ "epoch": 0.44081420977570335,
736
+ "step": 850
737
+ },
738
+ {
739
+ "loss": 1.5824,
740
+ "grad_norm": 0.9759206771850586,
741
+ "learning_rate": 6.180555555555557e-06,
742
+ "epoch": 0.44600025930247633,
743
+ "step": 860
744
+ },
745
+ {
746
+ "loss": 1.5217,
747
+ "grad_norm": 0.9516901969909668,
748
+ "learning_rate": 6.122685185185186e-06,
749
+ "epoch": 0.4511863088292493,
750
+ "step": 870
751
+ },
752
+ {
753
+ "loss": 1.5709,
754
+ "grad_norm": 0.906534731388092,
755
+ "learning_rate": 6.064814814814816e-06,
756
+ "epoch": 0.4563723583560223,
757
+ "step": 880
758
+ },
759
+ {
760
+ "loss": 1.5353,
761
+ "grad_norm": 0.9936981797218323,
762
+ "learning_rate": 6.006944444444445e-06,
763
+ "epoch": 0.4615584078827953,
764
+ "step": 890
765
+ },
766
+ {
767
+ "loss": 1.5552,
768
+ "grad_norm": 1.0134445428848267,
769
+ "learning_rate": 5.949074074074075e-06,
770
+ "epoch": 0.46674445740956827,
771
+ "step": 900
772
+ },
773
+ {
774
+ "eval_loss": 1.5813027620315552,
775
+ "eval_runtime": 86.3338,
776
+ "eval_samples_per_second": 79.413,
777
+ "eval_steps_per_second": 9.927,
778
+ "epoch": 0.46674445740956827,
779
+ "step": 900
780
+ },
781
+ {
782
+ "loss": 1.5927,
783
+ "grad_norm": 1.0366058349609375,
784
+ "learning_rate": 5.891203703703704e-06,
785
+ "epoch": 0.47193050693634125,
786
+ "step": 910
787
+ },
788
+ {
789
+ "loss": 1.632,
790
+ "grad_norm": 1.0132540464401245,
791
+ "learning_rate": 5.833333333333334e-06,
792
+ "epoch": 0.47711655646311424,
793
+ "step": 920
794
+ },
795
+ {
796
+ "loss": 1.4934,
797
+ "grad_norm": 1.1419975757598877,
798
+ "learning_rate": 5.775462962962963e-06,
799
+ "epoch": 0.4823026059898872,
800
+ "step": 930
801
+ },
802
+ {
803
+ "loss": 1.6463,
804
+ "grad_norm": 0.9270347952842712,
805
+ "learning_rate": 5.717592592592593e-06,
806
+ "epoch": 0.4874886555166602,
807
+ "step": 940
808
+ },
809
+ {
810
+ "loss": 1.5421,
811
+ "grad_norm": 0.9377948641777039,
812
+ "learning_rate": 5.659722222222222e-06,
813
+ "epoch": 0.4926747050434332,
814
+ "step": 950
815
+ },
816
+ {
817
+ "eval_loss": 1.5789639949798584,
818
+ "eval_runtime": 86.4079,
819
+ "eval_samples_per_second": 79.345,
820
+ "eval_steps_per_second": 9.918,
821
+ "epoch": 0.4926747050434332,
822
+ "step": 950
823
+ },
824
+ {
825
+ "loss": 1.5471,
826
+ "grad_norm": 0.9253595471382141,
827
+ "learning_rate": 5.601851851851853e-06,
828
+ "epoch": 0.4978607545702061,
829
+ "step": 960
830
+ },
831
+ {
832
+ "loss": 1.6027,
833
+ "grad_norm": 0.9463081955909729,
834
+ "learning_rate": 5.543981481481482e-06,
835
+ "epoch": 0.5030468040969791,
836
+ "step": 970
837
+ },
838
+ {
839
+ "loss": 1.5856,
840
+ "grad_norm": 1.020498514175415,
841
+ "learning_rate": 5.486111111111112e-06,
842
+ "epoch": 0.5082328536237521,
843
+ "step": 980
844
+ },
845
+ {
846
+ "loss": 1.501,
847
+ "grad_norm": 1.06349778175354,
848
+ "learning_rate": 5.428240740740741e-06,
849
+ "epoch": 0.5134189031505251,
850
+ "step": 990
851
+ },
852
+ {
853
+ "loss": 1.6204,
854
+ "grad_norm": 1.0478006601333618,
855
+ "learning_rate": 5.370370370370371e-06,
856
+ "epoch": 0.5186049526772981,
857
+ "step": 1000
858
+ },
859
+ {
860
+ "eval_loss": 1.5767922401428223,
861
+ "eval_runtime": 86.4434,
862
+ "eval_samples_per_second": 79.312,
863
+ "eval_steps_per_second": 9.914,
864
+ "epoch": 0.5186049526772981,
865
+ "step": 1000
866
+ },
867
+ {
868
+ "loss": 1.6251,
869
+ "grad_norm": 0.8741515874862671,
870
+ "learning_rate": 5.3125e-06,
871
+ "epoch": 0.523791002204071,
872
+ "step": 1010
873
+ },
874
+ {
875
+ "loss": 1.6024,
876
+ "grad_norm": 1.1460492610931396,
877
+ "learning_rate": 5.2546296296296295e-06,
878
+ "epoch": 0.5289770517308441,
879
+ "step": 1020
880
+ },
881
+ {
882
+ "loss": 1.6518,
883
+ "grad_norm": 0.9717974662780762,
884
+ "learning_rate": 5.1967592592592595e-06,
885
+ "epoch": 0.534163101257617,
886
+ "step": 1030
887
+ },
888
+ {
889
+ "loss": 1.5623,
890
+ "grad_norm": 1.108122706413269,
891
+ "learning_rate": 5.138888888888889e-06,
892
+ "epoch": 0.5393491507843899,
893
+ "step": 1040
894
+ },
895
+ {
896
+ "loss": 1.5669,
897
+ "grad_norm": 0.9962718486785889,
898
+ "learning_rate": 5.081018518518519e-06,
899
+ "epoch": 0.544535200311163,
900
+ "step": 1050
901
+ },
902
+ {
903
+ "eval_loss": 1.5750432014465332,
904
+ "eval_runtime": 86.3677,
905
+ "eval_samples_per_second": 79.382,
906
+ "eval_steps_per_second": 9.923,
907
+ "epoch": 0.544535200311163,
908
+ "step": 1050
909
+ },
910
+ {
911
+ "loss": 1.7621,
912
+ "grad_norm": 1.017765998840332,
913
+ "learning_rate": 5.023148148148148e-06,
914
+ "epoch": 0.5497212498379359,
915
+ "step": 1060
916
+ },
917
+ {
918
+ "loss": 1.6677,
919
+ "grad_norm": 0.9941328763961792,
920
+ "learning_rate": 4.9652777777777786e-06,
921
+ "epoch": 0.554907299364709,
922
+ "step": 1070
923
+ },
924
+ {
925
+ "loss": 1.5827,
926
+ "grad_norm": 0.9023691415786743,
927
+ "learning_rate": 4.907407407407408e-06,
928
+ "epoch": 0.5600933488914819,
929
+ "step": 1080
930
+ },
931
+ {
932
+ "loss": 1.5146,
933
+ "grad_norm": 0.9906938672065735,
934
+ "learning_rate": 4.849537037037038e-06,
935
+ "epoch": 0.5652793984182549,
936
+ "step": 1090
937
+ },
938
+ {
939
+ "loss": 1.6205,
940
+ "grad_norm": 1.0041205883026123,
941
+ "learning_rate": 4.791666666666668e-06,
942
+ "epoch": 0.5704654479450278,
943
+ "step": 1100
944
+ },
945
+ {
946
+ "eval_loss": 1.573021411895752,
947
+ "eval_runtime": 86.381,
948
+ "eval_samples_per_second": 79.369,
949
+ "eval_steps_per_second": 9.921,
950
+ "epoch": 0.5704654479450278,
951
+ "step": 1100
952
+ },
953
+ {
954
+ "loss": 1.4968,
955
+ "grad_norm": 0.9837663173675537,
956
+ "learning_rate": 4.733796296296297e-06,
957
+ "epoch": 0.5756514974718009,
958
+ "step": 1110
959
+ },
960
+ {
961
+ "loss": 1.5331,
962
+ "grad_norm": 1.030752182006836,
963
+ "learning_rate": 4.675925925925927e-06,
964
+ "epoch": 0.5808375469985738,
965
+ "step": 1120
966
+ },
967
+ {
968
+ "loss": 1.5154,
969
+ "grad_norm": 1.0442911386489868,
970
+ "learning_rate": 4.618055555555556e-06,
971
+ "epoch": 0.5860235965253469,
972
+ "step": 1130
973
+ },
974
+ {
975
+ "loss": 1.5524,
976
+ "grad_norm": 1.3084688186645508,
977
+ "learning_rate": 4.560185185185186e-06,
978
+ "epoch": 0.5912096460521198,
979
+ "step": 1140
980
+ },
981
+ {
982
+ "loss": 1.6502,
983
+ "grad_norm": 1.2625364065170288,
984
+ "learning_rate": 4.502314814814815e-06,
985
+ "epoch": 0.5963956955788928,
986
+ "step": 1150
987
+ },
988
+ {
989
+ "eval_loss": 1.5713461637496948,
990
+ "eval_runtime": 86.2319,
991
+ "eval_samples_per_second": 79.507,
992
+ "eval_steps_per_second": 9.938,
993
+ "epoch": 0.5963956955788928,
994
+ "step": 1150
995
+ },
996
+ {
997
+ "loss": 1.5517,
998
+ "grad_norm": 0.9740908741950989,
999
+ "learning_rate": 4.444444444444444e-06,
1000
+ "epoch": 0.6015817451056658,
1001
+ "step": 1160
1002
+ },
1003
+ {
1004
+ "loss": 1.5263,
1005
+ "grad_norm": 0.9409569501876831,
1006
+ "learning_rate": 4.386574074074074e-06,
1007
+ "epoch": 0.6067677946324388,
1008
+ "step": 1170
1009
+ },
1010
+ {
1011
+ "loss": 1.5642,
1012
+ "grad_norm": 1.0278596878051758,
1013
+ "learning_rate": 4.328703703703704e-06,
1014
+ "epoch": 0.6119538441592117,
1015
+ "step": 1180
1016
+ },
1017
+ {
1018
+ "loss": 1.4712,
1019
+ "grad_norm": 1.1742486953735352,
1020
+ "learning_rate": 4.270833333333333e-06,
1021
+ "epoch": 0.6171398936859847,
1022
+ "step": 1190
1023
+ },
1024
+ {
1025
+ "loss": 1.496,
1026
+ "grad_norm": 1.0322927236557007,
1027
+ "learning_rate": 4.212962962962963e-06,
1028
+ "epoch": 0.6223259432127577,
1029
+ "step": 1200
1030
+ },
1031
+ {
1032
+ "eval_loss": 1.569901704788208,
1033
+ "eval_runtime": 86.1974,
1034
+ "eval_samples_per_second": 79.538,
1035
+ "eval_steps_per_second": 9.942,
1036
+ "epoch": 0.6223259432127577,
1037
+ "step": 1200
1038
+ },
1039
+ {
1040
+ "loss": 1.5408,
1041
+ "grad_norm": 1.0326426029205322,
1042
+ "learning_rate": 4.155092592592593e-06,
1043
+ "epoch": 0.6275119927395306,
1044
+ "step": 1210
1045
+ },
1046
+ {
1047
+ "loss": 1.5513,
1048
+ "grad_norm": 1.157041072845459,
1049
+ "learning_rate": 4.097222222222222e-06,
1050
+ "epoch": 0.6326980422663037,
1051
+ "step": 1220
1052
+ },
1053
+ {
1054
+ "loss": 1.5587,
1055
+ "grad_norm": 0.9807701110839844,
1056
+ "learning_rate": 4.039351851851852e-06,
1057
+ "epoch": 0.6378840917930766,
1058
+ "step": 1230
1059
+ },
1060
+ {
1061
+ "loss": 1.5375,
1062
+ "grad_norm": 0.9729917049407959,
1063
+ "learning_rate": 3.9814814814814814e-06,
1064
+ "epoch": 0.6430701413198496,
1065
+ "step": 1240
1066
+ },
1067
+ {
1068
+ "loss": 1.5693,
1069
+ "grad_norm": 0.9340436458587646,
1070
+ "learning_rate": 3.9236111111111114e-06,
1071
+ "epoch": 0.6482561908466226,
1072
+ "step": 1250
1073
+ },
1074
+ {
1075
+ "eval_loss": 1.5686092376708984,
1076
+ "eval_runtime": 86.3527,
1077
+ "eval_samples_per_second": 79.395,
1078
+ "eval_steps_per_second": 9.924,
1079
+ "epoch": 0.6482561908466226,
1080
+ "step": 1250
1081
+ },
1082
+ {
1083
+ "loss": 1.5608,
1084
+ "grad_norm": 0.9910426139831543,
1085
+ "learning_rate": 3.865740740740741e-06,
1086
+ "epoch": 0.6534422403733956,
1087
+ "step": 1260
1088
+ },
1089
+ {
1090
+ "loss": 1.5789,
1091
+ "grad_norm": 1.0426393747329712,
1092
+ "learning_rate": 3.8078703703703705e-06,
1093
+ "epoch": 0.6586282899001685,
1094
+ "step": 1270
1095
+ },
1096
+ {
1097
+ "loss": 1.6392,
1098
+ "grad_norm": 1.0836423635482788,
1099
+ "learning_rate": 3.7500000000000005e-06,
1100
+ "epoch": 0.6638143394269416,
1101
+ "step": 1280
1102
+ },
1103
+ {
1104
+ "loss": 1.5159,
1105
+ "grad_norm": 0.9968803524971008,
1106
+ "learning_rate": 3.69212962962963e-06,
1107
+ "epoch": 0.6690003889537145,
1108
+ "step": 1290
1109
+ },
1110
+ {
1111
+ "loss": 1.512,
1112
+ "grad_norm": 0.9647068381309509,
1113
+ "learning_rate": 3.6342592592592596e-06,
1114
+ "epoch": 0.6741864384804875,
1115
+ "step": 1300
1116
+ },
1117
+ {
1118
+ "eval_loss": 1.5673084259033203,
1119
+ "eval_runtime": 86.3749,
1120
+ "eval_samples_per_second": 79.375,
1121
+ "eval_steps_per_second": 9.922,
1122
+ "epoch": 0.6741864384804875,
1123
+ "step": 1300
1124
+ },
1125
+ {
1126
+ "loss": 1.565,
1127
+ "grad_norm": 1.0944141149520874,
1128
+ "learning_rate": 3.576388888888889e-06,
1129
+ "epoch": 0.6793724880072605,
1130
+ "step": 1310
1131
+ },
1132
+ {
1133
+ "loss": 1.5287,
1134
+ "grad_norm": 1.2307634353637695,
1135
+ "learning_rate": 3.5185185185185187e-06,
1136
+ "epoch": 0.6845585375340334,
1137
+ "step": 1320
1138
+ },
1139
+ {
1140
+ "loss": 1.5402,
1141
+ "grad_norm": 1.0210680961608887,
1142
+ "learning_rate": 3.4606481481481487e-06,
1143
+ "epoch": 0.6897445870608064,
1144
+ "step": 1330
1145
+ },
1146
+ {
1147
+ "loss": 1.5251,
1148
+ "grad_norm": 1.0127681493759155,
1149
+ "learning_rate": 3.4027777777777783e-06,
1150
+ "epoch": 0.6949306365875794,
1151
+ "step": 1340
1152
+ },
1153
+ {
1154
+ "loss": 1.5393,
1155
+ "grad_norm": 1.1938350200653076,
1156
+ "learning_rate": 3.344907407407408e-06,
1157
+ "epoch": 0.7001166861143524,
1158
+ "step": 1350
1159
+ },
1160
+ {
1161
+ "eval_loss": 1.566351294517517,
1162
+ "eval_runtime": 86.3197,
1163
+ "eval_samples_per_second": 79.426,
1164
+ "eval_steps_per_second": 9.928,
1165
+ "epoch": 0.7001166861143524,
1166
+ "step": 1350
1167
+ },
1168
+ {
1169
+ "loss": 1.4706,
1170
+ "grad_norm": 1.1065889596939087,
1171
+ "learning_rate": 3.2870370370370374e-06,
1172
+ "epoch": 0.7053027356411253,
1173
+ "step": 1360
1174
+ },
1175
+ {
1176
+ "loss": 1.5842,
1177
+ "grad_norm": 1.072017788887024,
1178
+ "learning_rate": 3.229166666666667e-06,
1179
+ "epoch": 0.7104887851678984,
1180
+ "step": 1370
1181
+ },
1182
+ {
1183
+ "loss": 1.5889,
1184
+ "grad_norm": 1.0153334140777588,
1185
+ "learning_rate": 3.171296296296297e-06,
1186
+ "epoch": 0.7156748346946713,
1187
+ "step": 1380
1188
+ },
1189
+ {
1190
+ "loss": 1.6021,
1191
+ "grad_norm": 1.1801613569259644,
1192
+ "learning_rate": 3.1134259259259265e-06,
1193
+ "epoch": 0.7208608842214443,
1194
+ "step": 1390
1195
+ },
1196
+ {
1197
+ "loss": 1.4888,
1198
+ "grad_norm": 1.0696223974227905,
1199
+ "learning_rate": 3.055555555555556e-06,
1200
+ "epoch": 0.7260469337482173,
1201
+ "step": 1400
1202
+ },
1203
+ {
1204
+ "eval_loss": 1.5651835203170776,
1205
+ "eval_runtime": 86.2382,
1206
+ "eval_samples_per_second": 79.501,
1207
+ "eval_steps_per_second": 9.938,
1208
+ "epoch": 0.7260469337482173,
1209
+ "step": 1400
1210
+ },
1211
+ {
1212
+ "loss": 1.5563,
1213
+ "grad_norm": 1.246092438697815,
1214
+ "learning_rate": 2.9976851851851856e-06,
1215
+ "epoch": 0.7312329832749903,
1216
+ "step": 1410
1217
+ },
1218
+ {
1219
+ "loss": 1.6014,
1220
+ "grad_norm": 0.8846377730369568,
1221
+ "learning_rate": 2.9398148148148147e-06,
1222
+ "epoch": 0.7364190328017632,
1223
+ "step": 1420
1224
+ },
1225
+ {
1226
+ "loss": 1.5664,
1227
+ "grad_norm": 0.8743310570716858,
1228
+ "learning_rate": 2.8819444444444443e-06,
1229
+ "epoch": 0.7416050823285363,
1230
+ "step": 1430
1231
+ },
1232
+ {
1233
+ "loss": 1.4729,
1234
+ "grad_norm": 1.1290152072906494,
1235
+ "learning_rate": 2.8240740740740743e-06,
1236
+ "epoch": 0.7467911318553092,
1237
+ "step": 1440
1238
+ },
1239
+ {
1240
+ "loss": 1.5399,
1241
+ "grad_norm": 0.8955589532852173,
1242
+ "learning_rate": 2.766203703703704e-06,
1243
+ "epoch": 0.7519771813820822,
1244
+ "step": 1450
1245
+ },
1246
+ {
1247
+ "eval_loss": 1.5642883777618408,
1248
+ "eval_runtime": 86.3003,
1249
+ "eval_samples_per_second": 79.443,
1250
+ "eval_steps_per_second": 9.93,
1251
+ "epoch": 0.7519771813820822,
1252
+ "step": 1450
1253
+ },
1254
+ {
1255
+ "loss": 1.5275,
1256
+ "grad_norm": 1.09114670753479,
1257
+ "learning_rate": 2.7083333333333334e-06,
1258
+ "epoch": 0.7571632309088552,
1259
+ "step": 1460
1260
+ },
1261
+ {
1262
+ "loss": 1.6264,
1263
+ "grad_norm": 0.9536322355270386,
1264
+ "learning_rate": 2.650462962962963e-06,
1265
+ "epoch": 0.7623492804356281,
1266
+ "step": 1470
1267
+ },
1268
+ {
1269
+ "loss": 1.5143,
1270
+ "grad_norm": 1.1673610210418701,
1271
+ "learning_rate": 2.5925925925925925e-06,
1272
+ "epoch": 0.7675353299624011,
1273
+ "step": 1480
1274
+ },
1275
+ {
1276
+ "loss": 1.5566,
1277
+ "grad_norm": 1.0434508323669434,
1278
+ "learning_rate": 2.5347222222222225e-06,
1279
+ "epoch": 0.7727213794891741,
1280
+ "step": 1490
1281
+ },
1282
+ {
1283
+ "loss": 1.6804,
1284
+ "grad_norm": 1.1256870031356812,
1285
+ "learning_rate": 2.476851851851852e-06,
1286
+ "epoch": 0.7779074290159471,
1287
+ "step": 1500
1288
+ },
1289
+ {
1290
+ "eval_loss": 1.563399314880371,
1291
+ "eval_runtime": 86.4487,
1292
+ "eval_samples_per_second": 79.307,
1293
+ "eval_steps_per_second": 9.913,
1294
+ "epoch": 0.7779074290159471,
1295
+ "step": 1500
1296
+ },
1297
+ {
1298
+ "loss": 1.6603,
1299
+ "grad_norm": 0.8788173198699951,
1300
+ "learning_rate": 2.4189814814814816e-06,
1301
+ "epoch": 0.78309347854272,
1302
+ "step": 1510
1303
+ },
1304
+ {
1305
+ "loss": 1.6158,
1306
+ "grad_norm": 1.1211612224578857,
1307
+ "learning_rate": 2.361111111111111e-06,
1308
+ "epoch": 0.7882795280694931,
1309
+ "step": 1520
1310
+ },
1311
+ {
1312
+ "loss": 1.5677,
1313
+ "grad_norm": 1.0999435186386108,
1314
+ "learning_rate": 2.3032407407407407e-06,
1315
+ "epoch": 0.793465577596266,
1316
+ "step": 1530
1317
+ },
1318
+ {
1319
+ "loss": 1.5631,
1320
+ "grad_norm": 1.264574408531189,
1321
+ "learning_rate": 2.2453703703703707e-06,
1322
+ "epoch": 0.798651627123039,
1323
+ "step": 1540
1324
+ },
1325
+ {
1326
+ "loss": 1.5432,
1327
+ "grad_norm": 0.8702682256698608,
1328
+ "learning_rate": 2.1875000000000002e-06,
1329
+ "epoch": 0.803837676649812,
1330
+ "step": 1550
1331
+ },
1332
+ {
1333
+ "eval_loss": 1.562705159187317,
1334
+ "eval_runtime": 86.0644,
1335
+ "eval_samples_per_second": 79.661,
1336
+ "eval_steps_per_second": 9.958,
1337
+ "epoch": 0.803837676649812,
1338
+ "step": 1550
1339
+ },
1340
+ {
1341
+ "loss": 1.6092,
1342
+ "grad_norm": 1.0259442329406738,
1343
+ "learning_rate": 2.1296296296296298e-06,
1344
+ "epoch": 0.809023726176585,
1345
+ "step": 1560
1346
+ },
1347
+ {
1348
+ "loss": 1.5847,
1349
+ "grad_norm": 1.1580406427383423,
1350
+ "learning_rate": 2.0717592592592593e-06,
1351
+ "epoch": 0.814209775703358,
1352
+ "step": 1570
1353
+ },
1354
+ {
1355
+ "loss": 1.5151,
1356
+ "grad_norm": 0.967621922492981,
1357
+ "learning_rate": 2.0138888888888893e-06,
1358
+ "epoch": 0.819395825230131,
1359
+ "step": 1580
1360
+ },
1361
+ {
1362
+ "loss": 1.547,
1363
+ "grad_norm": 1.054157018661499,
1364
+ "learning_rate": 1.956018518518519e-06,
1365
+ "epoch": 0.8245818747569039,
1366
+ "step": 1590
1367
+ },
1368
+ {
1369
+ "loss": 1.5517,
1370
+ "grad_norm": 0.888331413269043,
1371
+ "learning_rate": 1.8981481481481484e-06,
1372
+ "epoch": 0.829767924283677,
1373
+ "step": 1600
1374
+ },
1375
+ {
1376
+ "eval_loss": 1.5619544982910156,
1377
+ "eval_runtime": 86.307,
1378
+ "eval_samples_per_second": 79.437,
1379
+ "eval_steps_per_second": 9.93,
1380
+ "epoch": 0.829767924283677,
1381
+ "step": 1600
1382
+ },
1383
+ {
1384
+ "loss": 1.5268,
1385
+ "grad_norm": 1.2048959732055664,
1386
+ "learning_rate": 1.840277777777778e-06,
1387
+ "epoch": 0.8349539738104499,
1388
+ "step": 1610
1389
+ },
1390
+ {
1391
+ "loss": 1.5325,
1392
+ "grad_norm": 0.9210975766181946,
1393
+ "learning_rate": 1.7824074074074073e-06,
1394
+ "epoch": 0.8401400233372228,
1395
+ "step": 1620
1396
+ },
1397
+ {
1398
+ "loss": 1.7056,
1399
+ "grad_norm": 1.251136302947998,
1400
+ "learning_rate": 1.724537037037037e-06,
1401
+ "epoch": 0.8453260728639959,
1402
+ "step": 1630
1403
+ },
1404
+ {
1405
+ "loss": 1.4827,
1406
+ "grad_norm": 1.1929717063903809,
1407
+ "learning_rate": 1.6666666666666667e-06,
1408
+ "epoch": 0.8505121223907688,
1409
+ "step": 1640
1410
+ },
1411
+ {
1412
+ "loss": 1.4766,
1413
+ "grad_norm": 1.0978388786315918,
1414
+ "learning_rate": 1.6087962962962964e-06,
1415
+ "epoch": 0.8556981719175418,
1416
+ "step": 1650
1417
+ },
1418
+ {
1419
+ "eval_loss": 1.5613240003585815,
1420
+ "eval_runtime": 86.2243,
1421
+ "eval_samples_per_second": 79.514,
1422
+ "eval_steps_per_second": 9.939,
1423
+ "epoch": 0.8556981719175418,
1424
+ "step": 1650
1425
+ },
1426
+ {
1427
+ "loss": 1.5595,
1428
+ "grad_norm": 0.9460042715072632,
1429
+ "learning_rate": 1.550925925925926e-06,
1430
+ "epoch": 0.8608842214443148,
1431
+ "step": 1660
1432
+ },
1433
+ {
1434
+ "loss": 1.533,
1435
+ "grad_norm": 0.9968504309654236,
1436
+ "learning_rate": 1.4930555555555555e-06,
1437
+ "epoch": 0.8660702709710878,
1438
+ "step": 1670
1439
+ },
1440
+ {
1441
+ "loss": 1.5617,
1442
+ "grad_norm": 1.0745750665664673,
1443
+ "learning_rate": 1.4351851851851853e-06,
1444
+ "epoch": 0.8712563204978607,
1445
+ "step": 1680
1446
+ },
1447
+ {
1448
+ "loss": 1.6192,
1449
+ "grad_norm": 1.036375880241394,
1450
+ "learning_rate": 1.3773148148148149e-06,
1451
+ "epoch": 0.8764423700246338,
1452
+ "step": 1690
1453
+ },
1454
+ {
1455
+ "loss": 1.5834,
1456
+ "grad_norm": 1.0536189079284668,
1457
+ "learning_rate": 1.3194444444444446e-06,
1458
+ "epoch": 0.8816284195514067,
1459
+ "step": 1700
1460
+ },
1461
+ {
1462
+ "eval_loss": 1.5608420372009277,
1463
+ "eval_runtime": 86.452,
1464
+ "eval_samples_per_second": 79.304,
1465
+ "eval_steps_per_second": 9.913,
1466
+ "epoch": 0.8816284195514067,
1467
+ "step": 1700
1468
+ },
1469
+ {
1470
+ "loss": 1.5061,
1471
+ "grad_norm": 0.954603374004364,
1472
+ "learning_rate": 1.2615740740740742e-06,
1473
+ "epoch": 0.8868144690781797,
1474
+ "step": 1710
1475
+ },
1476
+ {
1477
+ "loss": 1.6052,
1478
+ "grad_norm": 1.0621075630187988,
1479
+ "learning_rate": 1.2037037037037037e-06,
1480
+ "epoch": 0.8920005186049527,
1481
+ "step": 1720
1482
+ },
1483
+ {
1484
+ "loss": 1.7701,
1485
+ "grad_norm": 1.1732264757156372,
1486
+ "learning_rate": 1.1458333333333333e-06,
1487
+ "epoch": 0.8971865681317257,
1488
+ "step": 1730
1489
+ },
1490
+ {
1491
+ "loss": 1.5129,
1492
+ "grad_norm": 1.0416635274887085,
1493
+ "learning_rate": 1.087962962962963e-06,
1494
+ "epoch": 0.9023726176584986,
1495
+ "step": 1740
1496
+ },
1497
+ {
1498
+ "loss": 1.6024,
1499
+ "grad_norm": 0.9687952995300293,
1500
+ "learning_rate": 1.0300925925925926e-06,
1501
+ "epoch": 0.9075586671852717,
1502
+ "step": 1750
1503
+ },
1504
+ {
1505
+ "eval_loss": 1.5604712963104248,
1506
+ "eval_runtime": 86.4997,
1507
+ "eval_samples_per_second": 79.26,
1508
+ "eval_steps_per_second": 9.908,
1509
+ "epoch": 0.9075586671852717,
1510
+ "step": 1750
1511
+ },
1512
+ {
1513
+ "loss": 1.5476,
1514
+ "grad_norm": 1.0386537313461304,
1515
+ "learning_rate": 9.722222222222224e-07,
1516
+ "epoch": 0.9127447167120446,
1517
+ "step": 1760
1518
+ },
1519
+ {
1520
+ "loss": 1.5496,
1521
+ "grad_norm": 1.0910669565200806,
1522
+ "learning_rate": 9.14351851851852e-07,
1523
+ "epoch": 0.9179307662388175,
1524
+ "step": 1770
1525
+ },
1526
+ {
1527
+ "loss": 1.6249,
1528
+ "grad_norm": 0.998030960559845,
1529
+ "learning_rate": 8.564814814814816e-07,
1530
+ "epoch": 0.9231168157655906,
1531
+ "step": 1780
1532
+ },
1533
+ {
1534
+ "loss": 1.485,
1535
+ "grad_norm": 1.199540138244629,
1536
+ "learning_rate": 7.986111111111111e-07,
1537
+ "epoch": 0.9283028652923635,
1538
+ "step": 1790
1539
+ },
1540
+ {
1541
+ "loss": 1.6253,
1542
+ "grad_norm": 1.20003080368042,
1543
+ "learning_rate": 7.407407407407407e-07,
1544
+ "epoch": 0.9334889148191365,
1545
+ "step": 1800
1546
+ },
1547
+ {
1548
+ "eval_loss": 1.5601959228515625,
1549
+ "eval_runtime": 86.4234,
1550
+ "eval_samples_per_second": 79.33,
1551
+ "eval_steps_per_second": 9.916,
1552
+ "epoch": 0.9334889148191365,
1553
+ "step": 1800
1554
+ },
1555
+ {
1556
+ "loss": 1.5598,
1557
+ "grad_norm": 1.2243926525115967,
1558
+ "learning_rate": 6.828703703703704e-07,
1559
+ "epoch": 0.9386749643459095,
1560
+ "step": 1810
1561
+ },
1562
+ {
1563
+ "loss": 1.509,
1564
+ "grad_norm": 0.9302783608436584,
1565
+ "learning_rate": 6.25e-07,
1566
+ "epoch": 0.9438610138726825,
1567
+ "step": 1820
1568
+ },
1569
+ {
1570
+ "loss": 1.5348,
1571
+ "grad_norm": 1.1018292903900146,
1572
+ "learning_rate": 5.671296296296297e-07,
1573
+ "epoch": 0.9490470633994554,
1574
+ "step": 1830
1575
+ },
1576
+ {
1577
+ "loss": 1.5413,
1578
+ "grad_norm": 0.9914394617080688,
1579
+ "learning_rate": 5.092592592592593e-07,
1580
+ "epoch": 0.9542331129262285,
1581
+ "step": 1840
1582
+ },
1583
+ {
1584
+ "loss": 1.5812,
1585
+ "grad_norm": 1.0195194482803345,
1586
+ "learning_rate": 4.5138888888888893e-07,
1587
+ "epoch": 0.9594191624530014,
1588
+ "step": 1850
1589
+ },
1590
+ {
1591
+ "eval_loss": 1.560049295425415,
1592
+ "eval_runtime": 86.2646,
1593
+ "eval_samples_per_second": 79.476,
1594
+ "eval_steps_per_second": 9.935,
1595
+ "epoch": 0.9594191624530014,
1596
+ "step": 1850
1597
+ },
1598
+ {
1599
+ "loss": 1.5907,
1600
+ "grad_norm": 1.0537919998168945,
1601
+ "learning_rate": 3.9351851851851854e-07,
1602
+ "epoch": 0.9646052119797744,
1603
+ "step": 1860
1604
+ },
1605
+ {
1606
+ "loss": 1.5701,
1607
+ "grad_norm": 1.0531014204025269,
1608
+ "learning_rate": 3.356481481481482e-07,
1609
+ "epoch": 0.9697912615065474,
1610
+ "step": 1870
1611
+ },
1612
+ {
1613
+ "loss": 1.6686,
1614
+ "grad_norm": 1.1975234746932983,
1615
+ "learning_rate": 2.7777777777777776e-07,
1616
+ "epoch": 0.9749773110333204,
1617
+ "step": 1880
1618
+ },
1619
+ {
1620
+ "loss": 1.6079,
1621
+ "grad_norm": 1.044866919517517,
1622
+ "learning_rate": 2.1990740740740742e-07,
1623
+ "epoch": 0.9801633605600933,
1624
+ "step": 1890
1625
+ },
1626
+ {
1627
+ "loss": 1.6172,
1628
+ "grad_norm": 1.0296008586883545,
1629
+ "learning_rate": 1.6203703703703703e-07,
1630
+ "epoch": 0.9853494100868664,
1631
+ "step": 1900
1632
+ },
1633
+ {
1634
+ "eval_loss": 1.5599167346954346,
1635
+ "eval_runtime": 86.26,
1636
+ "eval_samples_per_second": 79.481,
1637
+ "eval_steps_per_second": 9.935,
1638
+ "epoch": 0.9853494100868664,
1639
+ "step": 1900
1640
+ },
1641
+ {
1642
+ "loss": 1.597,
1643
+ "grad_norm": 1.2206826210021973,
1644
+ "learning_rate": 1.0416666666666667e-07,
1645
+ "epoch": 0.9905354596136393,
1646
+ "step": 1910
1647
+ },
1648
+ {
1649
+ "loss": 1.5289,
1650
+ "grad_norm": 1.3176236152648926,
1651
+ "learning_rate": 4.6296296296296295e-08,
1652
+ "epoch": 0.9957215091404122,
1653
+ "step": 1920
1654
+ },
1655
+ {
1656
+ "train_runtime": 5251.9817,
1657
+ "train_samples_per_second": 11.748,
1658
+ "train_steps_per_second": 0.367,
1659
+ "total_flos": 1.8476343878064538e+17,
1660
+ "train_loss": 1.8777333230893147,
1661
+ "epoch": 0.9998703487618307,
1662
+ "step": 1928
1663
+ }
1664
+ ],
1665
+ "max_steps": 1928,
1666
+ "num_train_epochs": 1,
1667
+ "total_flos": 1.8476343878064538e+17,
1668
+ "trial_name": null,
1669
+ "trial_params": null
1670
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e770dc7f4064c75e2211207be0e79622cf6e4ef5bb7a652afe5e25beb51f5ea
3
+ size 5368
training_args_full.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/content/drive/My Drive/Hugh Mann/Llama3.2-1B-instruct-SMS-Young",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": true,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 8,
10
+ "per_device_eval_batch_size": 8,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 4,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.05,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.999,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 0.5,
23
+ "num_train_epochs": 1,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "linear",
26
+ "lr_scheduler_kwargs": {},
27
+ "warmup_ratio": 0.0,
28
+ "warmup_steps": 200,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/content/drive/My Drive/Hugh Mann/Llama3.2-1B-instruct-SMS-Young/runs/Dec06_23-44-48_e067531f1937",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": false,
35
+ "logging_steps": 10,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 1000,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": null,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": false,
52
+ "fp16": true,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": [],
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 50,
65
+ "dataloader_num_workers": 0,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/content/drive/My Drive/Hugh Mann/Llama3.2-1B-instruct-SMS-Young",
69
+ "disable_tqdm": false,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": true,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": [],
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": {
79
+ "min_num_params": 0,
80
+ "xla": false,
81
+ "xla_fsdp_v2": false,
82
+ "xla_fsdp_grad_ckpt": false
83
+ },
84
+ "fsdp_transformer_layer_cls_to_wrap": null,
85
+ "accelerator_config": {
86
+ "split_batches": false,
87
+ "dispatch_batches": null,
88
+ "even_batches": true,
89
+ "use_seedable_sampler": true,
90
+ "non_blocking": false,
91
+ "gradient_accumulation_kwargs": null
92
+ },
93
+ "deepspeed": null,
94
+ "label_smoothing_factor": 0.0,
95
+ "optim": "adamw_torch",
96
+ "optim_args": null,
97
+ "adafactor": false,
98
+ "group_by_length": false,
99
+ "length_column_name": "length",
100
+ "report_to": [
101
+ "wandb"
102
+ ],
103
+ "ddp_find_unused_parameters": null,
104
+ "ddp_bucket_cap_mb": null,
105
+ "ddp_broadcast_buffers": null,
106
+ "dataloader_pin_memory": true,
107
+ "dataloader_persistent_workers": false,
108
+ "skip_memory_metrics": true,
109
+ "use_legacy_prediction_loop": false,
110
+ "push_to_hub": false,
111
+ "resume_from_checkpoint": null,
112
+ "hub_model_id": null,
113
+ "hub_strategy": "every_save",
114
+ "hub_token": "<HUB_TOKEN>",
115
+ "hub_private_repo": false,
116
+ "hub_always_push": false,
117
+ "gradient_checkpointing": false,
118
+ "gradient_checkpointing_kwargs": null,
119
+ "include_inputs_for_metrics": false,
120
+ "include_for_metrics": [],
121
+ "eval_do_concat_batches": true,
122
+ "fp16_backend": "auto",
123
+ "evaluation_strategy": "steps",
124
+ "push_to_hub_model_id": null,
125
+ "push_to_hub_organization": null,
126
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
127
+ "mp_parameters": "",
128
+ "auto_find_batch_size": false,
129
+ "full_determinism": false,
130
+ "torchdynamo": null,
131
+ "ray_scope": "last",
132
+ "ddp_timeout": 1800,
133
+ "torch_compile": false,
134
+ "torch_compile_backend": null,
135
+ "torch_compile_mode": null,
136
+ "dispatch_batches": null,
137
+ "split_batches": null,
138
+ "include_tokens_per_second": false,
139
+ "include_num_input_tokens_seen": false,
140
+ "neftune_noise_alpha": null,
141
+ "optim_target_modules": null,
142
+ "batch_eval_metrics": false,
143
+ "eval_on_start": false,
144
+ "use_liger_kernel": false,
145
+ "eval_use_gather_object": false,
146
+ "average_tokens_across_devices": false
147
+ }