rat45 commited on
Commit
9d2326b
·
verified ·
1 Parent(s): 42899be

Upload folder using huggingface_hub

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 4332405321474048.0,
3
+ "train_loss": 0.7900132229251247,
4
+ "train_runtime": 706.4309,
5
+ "train_samples": 1000,
6
+ "train_samples_per_second": 4.247,
7
+ "train_steps_per_second": 0.263
8
+ }
checkpoint-186/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
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 0.14.0
checkpoint-186/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "o_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-186/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1cf83828fe88ffc61df67e2c3a15805b46ba53fccd1e03a1ec9a507351f66a
3
+ size 9034304
checkpoint-186/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4ae1d203127a5705c90de64f236f39eab9ad7b7af52367a5625a05db2e2b44
3
+ size 18170234
checkpoint-186/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0f9522c153da97f23da8012dc6d956211cbe4c1613eacd705217bc410d796c
3
+ size 14244
checkpoint-186/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef08939e76bb78603bc3bdd1e5486d1ec5566f2daa8f0334f68666b295ff9d5
3
+ size 988
checkpoint-186/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c0cf824c67c5f46bd906575c2f888f1acf32bdbcb24dc3cc063b4a3e2ced87
3
+ size 1064
checkpoint-186/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-186/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-186/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-186/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "extra_special_tokens": {},
36
+ "legacy": false,
37
+ "model_max_length": 2048,
38
+ "pad_token": "</s>",
39
+ "padding_side": "right",
40
+ "sp_model_kwargs": {},
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
checkpoint-186/trainer_state.json ADDED
@@ -0,0 +1,367 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.96,
6
+ "eval_steps": 500,
7
+ "global_step": 186,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.44993048906326294,
15
+ "learning_rate": 1.9977186146800707e-05,
16
+ "loss": 1.1852,
17
+ "mean_token_accuracy": 0.7368780478835106,
18
+ "num_tokens": 16177.0,
19
+ "step": 5
20
+ },
21
+ {
22
+ "epoch": 0.16,
23
+ "grad_norm": 0.446072518825531,
24
+ "learning_rate": 1.9884683243281117e-05,
25
+ "loss": 1.1334,
26
+ "mean_token_accuracy": 0.7490372791886329,
27
+ "num_tokens": 32676.0,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 0.24,
32
+ "grad_norm": 0.5208024978637695,
33
+ "learning_rate": 1.9721724257579907e-05,
34
+ "loss": 1.1397,
35
+ "mean_token_accuracy": 0.7374951928853989,
36
+ "num_tokens": 48484.0,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.32,
41
+ "grad_norm": 0.5335091352462769,
42
+ "learning_rate": 1.9489470729364694e-05,
43
+ "loss": 1.1291,
44
+ "mean_token_accuracy": 0.7498478129506111,
45
+ "num_tokens": 64399.0,
46
+ "step": 20
47
+ },
48
+ {
49
+ "epoch": 0.4,
50
+ "grad_norm": 0.6421738266944885,
51
+ "learning_rate": 1.918957811620231e-05,
52
+ "loss": 1.094,
53
+ "mean_token_accuracy": 0.7465715885162354,
54
+ "num_tokens": 80038.0,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 0.48,
59
+ "grad_norm": 0.5590124726295471,
60
+ "learning_rate": 1.8824183993782193e-05,
61
+ "loss": 1.0891,
62
+ "mean_token_accuracy": 0.7500069707632064,
63
+ "num_tokens": 95591.0,
64
+ "step": 30
65
+ },
66
+ {
67
+ "epoch": 0.56,
68
+ "grad_norm": 0.5460164546966553,
69
+ "learning_rate": 1.839589281969639e-05,
70
+ "loss": 1.0278,
71
+ "mean_token_accuracy": 0.7575115114450455,
72
+ "num_tokens": 111483.0,
73
+ "step": 35
74
+ },
75
+ {
76
+ "epoch": 0.64,
77
+ "grad_norm": 0.6239035129547119,
78
+ "learning_rate": 1.7907757369376984e-05,
79
+ "loss": 0.9952,
80
+ "mean_token_accuracy": 0.7626694276928901,
81
+ "num_tokens": 128244.0,
82
+ "step": 40
83
+ },
84
+ {
85
+ "epoch": 0.72,
86
+ "grad_norm": 0.6833351254463196,
87
+ "learning_rate": 1.7363256976511972e-05,
88
+ "loss": 1.0109,
89
+ "mean_token_accuracy": 0.760352547466755,
90
+ "num_tokens": 142495.0,
91
+ "step": 45
92
+ },
93
+ {
94
+ "epoch": 0.8,
95
+ "grad_norm": 0.6993600130081177,
96
+ "learning_rate": 1.6766272733037575e-05,
97
+ "loss": 0.9705,
98
+ "mean_token_accuracy": 0.768488883972168,
99
+ "num_tokens": 158074.0,
100
+ "step": 50
101
+ },
102
+ {
103
+ "epoch": 0.88,
104
+ "grad_norm": 0.7641519904136658,
105
+ "learning_rate": 1.612105982547663e-05,
106
+ "loss": 0.8792,
107
+ "mean_token_accuracy": 0.7812322407960892,
108
+ "num_tokens": 174411.0,
109
+ "step": 55
110
+ },
111
+ {
112
+ "epoch": 0.96,
113
+ "grad_norm": 0.8612833023071289,
114
+ "learning_rate": 1.543221720480419e-05,
115
+ "loss": 0.8912,
116
+ "mean_token_accuracy": 0.787124752998352,
117
+ "num_tokens": 189480.0,
118
+ "step": 60
119
+ },
120
+ {
121
+ "epoch": 1.032,
122
+ "grad_norm": 0.9852380752563477,
123
+ "learning_rate": 1.4704654806027558e-05,
124
+ "loss": 0.8234,
125
+ "mean_token_accuracy": 0.7974502179357741,
126
+ "num_tokens": 203798.0,
127
+ "step": 65
128
+ },
129
+ {
130
+ "epoch": 1.112,
131
+ "grad_norm": 0.8131120204925537,
132
+ "learning_rate": 1.3943558551133186e-05,
133
+ "loss": 0.8048,
134
+ "mean_token_accuracy": 0.8055687263607979,
135
+ "num_tokens": 219483.0,
136
+ "step": 70
137
+ },
138
+ {
139
+ "epoch": 1.192,
140
+ "grad_norm": 1.0975677967071533,
141
+ "learning_rate": 1.3154353384852559e-05,
142
+ "loss": 0.7795,
143
+ "mean_token_accuracy": 0.8085009381175041,
144
+ "num_tokens": 234730.0,
145
+ "step": 75
146
+ },
147
+ {
148
+ "epoch": 1.272,
149
+ "grad_norm": 0.8204861879348755,
150
+ "learning_rate": 1.2342664606720823e-05,
151
+ "loss": 0.7457,
152
+ "mean_token_accuracy": 0.822769646346569,
153
+ "num_tokens": 250096.0,
154
+ "step": 80
155
+ },
156
+ {
157
+ "epoch": 1.3519999999999999,
158
+ "grad_norm": 0.7401573061943054,
159
+ "learning_rate": 1.1514277775045768e-05,
160
+ "loss": 0.7079,
161
+ "mean_token_accuracy": 0.8261085689067841,
162
+ "num_tokens": 266076.0,
163
+ "step": 85
164
+ },
165
+ {
166
+ "epoch": 1.432,
167
+ "grad_norm": 0.6010871529579163,
168
+ "learning_rate": 1.0675097468583653e-05,
169
+ "loss": 0.7074,
170
+ "mean_token_accuracy": 0.8272138416767121,
171
+ "num_tokens": 281385.0,
172
+ "step": 90
173
+ },
174
+ {
175
+ "epoch": 1.512,
176
+ "grad_norm": 0.5529438257217407,
177
+ "learning_rate": 9.83110519986069e-06,
178
+ "loss": 0.6664,
179
+ "mean_token_accuracy": 0.8329674065113067,
180
+ "num_tokens": 296647.0,
181
+ "step": 95
182
+ },
183
+ {
184
+ "epoch": 1.592,
185
+ "grad_norm": 0.5067458152770996,
186
+ "learning_rate": 8.98831678012568e-06,
187
+ "loss": 0.6526,
188
+ "mean_token_accuracy": 0.8348439291119576,
189
+ "num_tokens": 312067.0,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 1.6720000000000002,
194
+ "grad_norm": 0.5340730547904968,
195
+ "learning_rate": 8.15273943982811e-06,
196
+ "loss": 0.675,
197
+ "mean_token_accuracy": 0.8353347033262253,
198
+ "num_tokens": 327458.0,
199
+ "step": 105
200
+ },
201
+ {
202
+ "epoch": 1.752,
203
+ "grad_norm": 0.4149323105812073,
204
+ "learning_rate": 7.330329010258483e-06,
205
+ "loss": 0.6392,
206
+ "mean_token_accuracy": 0.8354402139782906,
207
+ "num_tokens": 344098.0,
208
+ "step": 110
209
+ },
210
+ {
211
+ "epoch": 1.8319999999999999,
212
+ "grad_norm": 0.42973241209983826,
213
+ "learning_rate": 6.526947471551799e-06,
214
+ "loss": 0.6585,
215
+ "mean_token_accuracy": 0.8377262473106384,
216
+ "num_tokens": 359964.0,
217
+ "step": 115
218
+ },
219
+ {
220
+ "epoch": 1.912,
221
+ "grad_norm": 0.38989219069480896,
222
+ "learning_rate": 5.748321169643596e-06,
223
+ "loss": 0.6001,
224
+ "mean_token_accuracy": 0.8486244857311249,
225
+ "num_tokens": 376782.0,
226
+ "step": 120
227
+ },
228
+ {
229
+ "epoch": 1.992,
230
+ "grad_norm": 0.3842228651046753,
231
+ "learning_rate": 5.000000000000003e-06,
232
+ "loss": 0.6408,
233
+ "mean_token_accuracy": 0.8384670644998551,
234
+ "num_tokens": 393357.0,
235
+ "step": 125
236
+ },
237
+ {
238
+ "epoch": 2.064,
239
+ "grad_norm": 0.386435866355896,
240
+ "learning_rate": 4.287317849052075e-06,
241
+ "loss": 0.6318,
242
+ "mean_token_accuracy": 0.8400428146123886,
243
+ "num_tokens": 408486.0,
244
+ "step": 130
245
+ },
246
+ {
247
+ "epoch": 2.144,
248
+ "grad_norm": 0.4155893325805664,
249
+ "learning_rate": 3.6153545753001663e-06,
250
+ "loss": 0.6365,
251
+ "mean_token_accuracy": 0.8424267500638962,
252
+ "num_tokens": 423462.0,
253
+ "step": 135
254
+ },
255
+ {
256
+ "epoch": 2.224,
257
+ "grad_norm": 0.42164576053619385,
258
+ "learning_rate": 2.9888998010794745e-06,
259
+ "loss": 0.65,
260
+ "mean_token_accuracy": 0.8395944103598595,
261
+ "num_tokens": 439308.0,
262
+ "step": 140
263
+ },
264
+ {
265
+ "epoch": 2.304,
266
+ "grad_norm": 0.40206339955329895,
267
+ "learning_rate": 2.4124187730720916e-06,
268
+ "loss": 0.6441,
269
+ "mean_token_accuracy": 0.8418430313467979,
270
+ "num_tokens": 454859.0,
271
+ "step": 145
272
+ },
273
+ {
274
+ "epoch": 2.384,
275
+ "grad_norm": 0.41322216391563416,
276
+ "learning_rate": 1.8900205349049904e-06,
277
+ "loss": 0.6169,
278
+ "mean_token_accuracy": 0.8490483820438385,
279
+ "num_tokens": 470548.0,
280
+ "step": 150
281
+ },
282
+ {
283
+ "epoch": 2.464,
284
+ "grad_norm": 0.4834882915019989,
285
+ "learning_rate": 1.425428638693489e-06,
286
+ "loss": 0.6545,
287
+ "mean_token_accuracy": 0.8358306258916854,
288
+ "num_tokens": 485169.0,
289
+ "step": 155
290
+ },
291
+ {
292
+ "epoch": 2.544,
293
+ "grad_norm": 0.41212084889411926,
294
+ "learning_rate": 1.0219546042925842e-06,
295
+ "loss": 0.6087,
296
+ "mean_token_accuracy": 0.8500525638461113,
297
+ "num_tokens": 501284.0,
298
+ "step": 160
299
+ },
300
+ {
301
+ "epoch": 2.624,
302
+ "grad_norm": 0.4313817620277405,
303
+ "learning_rate": 6.824743154333157e-07,
304
+ "loss": 0.6387,
305
+ "mean_token_accuracy": 0.8408319368958473,
306
+ "num_tokens": 517799.0,
307
+ "step": 165
308
+ },
309
+ {
310
+ "epoch": 2.7039999999999997,
311
+ "grad_norm": 0.38043487071990967,
312
+ "learning_rate": 4.094075209879789e-07,
313
+ "loss": 0.5942,
314
+ "mean_token_accuracy": 0.8503163874149322,
315
+ "num_tokens": 534446.0,
316
+ "step": 170
317
+ },
318
+ {
319
+ "epoch": 2.784,
320
+ "grad_norm": 0.38836878538131714,
321
+ "learning_rate": 2.0470058747505516e-07,
322
+ "loss": 0.6464,
323
+ "mean_token_accuracy": 0.8419791996479035,
324
+ "num_tokens": 549141.0,
325
+ "step": 175
326
+ },
327
+ {
328
+ "epoch": 2.864,
329
+ "grad_norm": 0.4290372133255005,
330
+ "learning_rate": 6.981262574066395e-08,
331
+ "loss": 0.657,
332
+ "mean_token_accuracy": 0.8399893954396248,
333
+ "num_tokens": 564279.0,
334
+ "step": 180
335
+ },
336
+ {
337
+ "epoch": 2.944,
338
+ "grad_norm": 0.3860047161579132,
339
+ "learning_rate": 5.705090702819993e-09,
340
+ "loss": 0.6336,
341
+ "mean_token_accuracy": 0.8413404822349548,
342
+ "num_tokens": 580854.0,
343
+ "step": 185
344
+ }
345
+ ],
346
+ "logging_steps": 5,
347
+ "max_steps": 186,
348
+ "num_input_tokens_seen": 0,
349
+ "num_train_epochs": 3,
350
+ "save_steps": 500,
351
+ "stateful_callbacks": {
352
+ "TrainerControl": {
353
+ "args": {
354
+ "should_epoch_stop": false,
355
+ "should_evaluate": false,
356
+ "should_log": false,
357
+ "should_save": true,
358
+ "should_training_stop": true
359
+ },
360
+ "attributes": {}
361
+ }
362
+ },
363
+ "total_flos": 4332405321474048.0,
364
+ "train_batch_size": 2,
365
+ "trial_name": null,
366
+ "trial_params": null
367
+ }
checkpoint-186/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d9b2305ab7b370b5a8224f91319211b4ad270c40b7bada24475e498ac9e95a
3
+ size 5624
runs/Apr11_08-10-11_ad6845ae40d3/events.out.tfevents.1744359041.ad6845ae40d3.1012.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1347e7fb699ab25bed2db428bac2e7bd416ca071524bf749b8ebf86274fc04e
3
+ size 18423
sql-sft-loraTinyLlama/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "float32",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": null,
38
+ "rope_theta": 10000.0,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.51.2",
42
+ "use_cache": false,
43
+ "vocab_size": 32000
44
+ }
sql-sft-loraTinyLlama/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.51.2"
7
+ }
sql-sft-loraTinyLlama/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbaf2730400f52f42fa33d659ee7413a9b345ff78991346035dd899394125bf6
3
+ size 1078792880
sql-sft-loraTinyLlama/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
sql-sft-loraTinyLlama/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
sql-sft-loraTinyLlama/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
sql-sft-loraTinyLlama/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "extra_special_tokens": {},
36
+ "legacy": false,
37
+ "model_max_length": 2048,
38
+ "pad_token": "</s>",
39
+ "padding_side": "right",
40
+ "sp_model_kwargs": {},
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 4332405321474048.0,
3
+ "train_loss": 0.7900132229251247,
4
+ "train_runtime": 706.4309,
5
+ "train_samples": 1000,
6
+ "train_samples_per_second": 4.247,
7
+ "train_steps_per_second": 0.263
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,378 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.96,
6
+ "eval_steps": 500,
7
+ "global_step": 186,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 0.44993048906326294,
15
+ "learning_rate": 1.9977186146800707e-05,
16
+ "loss": 1.1852,
17
+ "mean_token_accuracy": 0.7368780478835106,
18
+ "num_tokens": 16177.0,
19
+ "step": 5
20
+ },
21
+ {
22
+ "epoch": 0.16,
23
+ "grad_norm": 0.446072518825531,
24
+ "learning_rate": 1.9884683243281117e-05,
25
+ "loss": 1.1334,
26
+ "mean_token_accuracy": 0.7490372791886329,
27
+ "num_tokens": 32676.0,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 0.24,
32
+ "grad_norm": 0.5208024978637695,
33
+ "learning_rate": 1.9721724257579907e-05,
34
+ "loss": 1.1397,
35
+ "mean_token_accuracy": 0.7374951928853989,
36
+ "num_tokens": 48484.0,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.32,
41
+ "grad_norm": 0.5335091352462769,
42
+ "learning_rate": 1.9489470729364694e-05,
43
+ "loss": 1.1291,
44
+ "mean_token_accuracy": 0.7498478129506111,
45
+ "num_tokens": 64399.0,
46
+ "step": 20
47
+ },
48
+ {
49
+ "epoch": 0.4,
50
+ "grad_norm": 0.6421738266944885,
51
+ "learning_rate": 1.918957811620231e-05,
52
+ "loss": 1.094,
53
+ "mean_token_accuracy": 0.7465715885162354,
54
+ "num_tokens": 80038.0,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 0.48,
59
+ "grad_norm": 0.5590124726295471,
60
+ "learning_rate": 1.8824183993782193e-05,
61
+ "loss": 1.0891,
62
+ "mean_token_accuracy": 0.7500069707632064,
63
+ "num_tokens": 95591.0,
64
+ "step": 30
65
+ },
66
+ {
67
+ "epoch": 0.56,
68
+ "grad_norm": 0.5460164546966553,
69
+ "learning_rate": 1.839589281969639e-05,
70
+ "loss": 1.0278,
71
+ "mean_token_accuracy": 0.7575115114450455,
72
+ "num_tokens": 111483.0,
73
+ "step": 35
74
+ },
75
+ {
76
+ "epoch": 0.64,
77
+ "grad_norm": 0.6239035129547119,
78
+ "learning_rate": 1.7907757369376984e-05,
79
+ "loss": 0.9952,
80
+ "mean_token_accuracy": 0.7626694276928901,
81
+ "num_tokens": 128244.0,
82
+ "step": 40
83
+ },
84
+ {
85
+ "epoch": 0.72,
86
+ "grad_norm": 0.6833351254463196,
87
+ "learning_rate": 1.7363256976511972e-05,
88
+ "loss": 1.0109,
89
+ "mean_token_accuracy": 0.760352547466755,
90
+ "num_tokens": 142495.0,
91
+ "step": 45
92
+ },
93
+ {
94
+ "epoch": 0.8,
95
+ "grad_norm": 0.6993600130081177,
96
+ "learning_rate": 1.6766272733037575e-05,
97
+ "loss": 0.9705,
98
+ "mean_token_accuracy": 0.768488883972168,
99
+ "num_tokens": 158074.0,
100
+ "step": 50
101
+ },
102
+ {
103
+ "epoch": 0.88,
104
+ "grad_norm": 0.7641519904136658,
105
+ "learning_rate": 1.612105982547663e-05,
106
+ "loss": 0.8792,
107
+ "mean_token_accuracy": 0.7812322407960892,
108
+ "num_tokens": 174411.0,
109
+ "step": 55
110
+ },
111
+ {
112
+ "epoch": 0.96,
113
+ "grad_norm": 0.8612833023071289,
114
+ "learning_rate": 1.543221720480419e-05,
115
+ "loss": 0.8912,
116
+ "mean_token_accuracy": 0.787124752998352,
117
+ "num_tokens": 189480.0,
118
+ "step": 60
119
+ },
120
+ {
121
+ "epoch": 1.032,
122
+ "grad_norm": 0.9852380752563477,
123
+ "learning_rate": 1.4704654806027558e-05,
124
+ "loss": 0.8234,
125
+ "mean_token_accuracy": 0.7974502179357741,
126
+ "num_tokens": 203798.0,
127
+ "step": 65
128
+ },
129
+ {
130
+ "epoch": 1.112,
131
+ "grad_norm": 0.8131120204925537,
132
+ "learning_rate": 1.3943558551133186e-05,
133
+ "loss": 0.8048,
134
+ "mean_token_accuracy": 0.8055687263607979,
135
+ "num_tokens": 219483.0,
136
+ "step": 70
137
+ },
138
+ {
139
+ "epoch": 1.192,
140
+ "grad_norm": 1.0975677967071533,
141
+ "learning_rate": 1.3154353384852559e-05,
142
+ "loss": 0.7795,
143
+ "mean_token_accuracy": 0.8085009381175041,
144
+ "num_tokens": 234730.0,
145
+ "step": 75
146
+ },
147
+ {
148
+ "epoch": 1.272,
149
+ "grad_norm": 0.8204861879348755,
150
+ "learning_rate": 1.2342664606720823e-05,
151
+ "loss": 0.7457,
152
+ "mean_token_accuracy": 0.822769646346569,
153
+ "num_tokens": 250096.0,
154
+ "step": 80
155
+ },
156
+ {
157
+ "epoch": 1.3519999999999999,
158
+ "grad_norm": 0.7401573061943054,
159
+ "learning_rate": 1.1514277775045768e-05,
160
+ "loss": 0.7079,
161
+ "mean_token_accuracy": 0.8261085689067841,
162
+ "num_tokens": 266076.0,
163
+ "step": 85
164
+ },
165
+ {
166
+ "epoch": 1.432,
167
+ "grad_norm": 0.6010871529579163,
168
+ "learning_rate": 1.0675097468583653e-05,
169
+ "loss": 0.7074,
170
+ "mean_token_accuracy": 0.8272138416767121,
171
+ "num_tokens": 281385.0,
172
+ "step": 90
173
+ },
174
+ {
175
+ "epoch": 1.512,
176
+ "grad_norm": 0.5529438257217407,
177
+ "learning_rate": 9.83110519986069e-06,
178
+ "loss": 0.6664,
179
+ "mean_token_accuracy": 0.8329674065113067,
180
+ "num_tokens": 296647.0,
181
+ "step": 95
182
+ },
183
+ {
184
+ "epoch": 1.592,
185
+ "grad_norm": 0.5067458152770996,
186
+ "learning_rate": 8.98831678012568e-06,
187
+ "loss": 0.6526,
188
+ "mean_token_accuracy": 0.8348439291119576,
189
+ "num_tokens": 312067.0,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 1.6720000000000002,
194
+ "grad_norm": 0.5340730547904968,
195
+ "learning_rate": 8.15273943982811e-06,
196
+ "loss": 0.675,
197
+ "mean_token_accuracy": 0.8353347033262253,
198
+ "num_tokens": 327458.0,
199
+ "step": 105
200
+ },
201
+ {
202
+ "epoch": 1.752,
203
+ "grad_norm": 0.4149323105812073,
204
+ "learning_rate": 7.330329010258483e-06,
205
+ "loss": 0.6392,
206
+ "mean_token_accuracy": 0.8354402139782906,
207
+ "num_tokens": 344098.0,
208
+ "step": 110
209
+ },
210
+ {
211
+ "epoch": 1.8319999999999999,
212
+ "grad_norm": 0.42973241209983826,
213
+ "learning_rate": 6.526947471551799e-06,
214
+ "loss": 0.6585,
215
+ "mean_token_accuracy": 0.8377262473106384,
216
+ "num_tokens": 359964.0,
217
+ "step": 115
218
+ },
219
+ {
220
+ "epoch": 1.912,
221
+ "grad_norm": 0.38989219069480896,
222
+ "learning_rate": 5.748321169643596e-06,
223
+ "loss": 0.6001,
224
+ "mean_token_accuracy": 0.8486244857311249,
225
+ "num_tokens": 376782.0,
226
+ "step": 120
227
+ },
228
+ {
229
+ "epoch": 1.992,
230
+ "grad_norm": 0.3842228651046753,
231
+ "learning_rate": 5.000000000000003e-06,
232
+ "loss": 0.6408,
233
+ "mean_token_accuracy": 0.8384670644998551,
234
+ "num_tokens": 393357.0,
235
+ "step": 125
236
+ },
237
+ {
238
+ "epoch": 2.064,
239
+ "grad_norm": 0.386435866355896,
240
+ "learning_rate": 4.287317849052075e-06,
241
+ "loss": 0.6318,
242
+ "mean_token_accuracy": 0.8400428146123886,
243
+ "num_tokens": 408486.0,
244
+ "step": 130
245
+ },
246
+ {
247
+ "epoch": 2.144,
248
+ "grad_norm": 0.4155893325805664,
249
+ "learning_rate": 3.6153545753001663e-06,
250
+ "loss": 0.6365,
251
+ "mean_token_accuracy": 0.8424267500638962,
252
+ "num_tokens": 423462.0,
253
+ "step": 135
254
+ },
255
+ {
256
+ "epoch": 2.224,
257
+ "grad_norm": 0.42164576053619385,
258
+ "learning_rate": 2.9888998010794745e-06,
259
+ "loss": 0.65,
260
+ "mean_token_accuracy": 0.8395944103598595,
261
+ "num_tokens": 439308.0,
262
+ "step": 140
263
+ },
264
+ {
265
+ "epoch": 2.304,
266
+ "grad_norm": 0.40206339955329895,
267
+ "learning_rate": 2.4124187730720916e-06,
268
+ "loss": 0.6441,
269
+ "mean_token_accuracy": 0.8418430313467979,
270
+ "num_tokens": 454859.0,
271
+ "step": 145
272
+ },
273
+ {
274
+ "epoch": 2.384,
275
+ "grad_norm": 0.41322216391563416,
276
+ "learning_rate": 1.8900205349049904e-06,
277
+ "loss": 0.6169,
278
+ "mean_token_accuracy": 0.8490483820438385,
279
+ "num_tokens": 470548.0,
280
+ "step": 150
281
+ },
282
+ {
283
+ "epoch": 2.464,
284
+ "grad_norm": 0.4834882915019989,
285
+ "learning_rate": 1.425428638693489e-06,
286
+ "loss": 0.6545,
287
+ "mean_token_accuracy": 0.8358306258916854,
288
+ "num_tokens": 485169.0,
289
+ "step": 155
290
+ },
291
+ {
292
+ "epoch": 2.544,
293
+ "grad_norm": 0.41212084889411926,
294
+ "learning_rate": 1.0219546042925842e-06,
295
+ "loss": 0.6087,
296
+ "mean_token_accuracy": 0.8500525638461113,
297
+ "num_tokens": 501284.0,
298
+ "step": 160
299
+ },
300
+ {
301
+ "epoch": 2.624,
302
+ "grad_norm": 0.4313817620277405,
303
+ "learning_rate": 6.824743154333157e-07,
304
+ "loss": 0.6387,
305
+ "mean_token_accuracy": 0.8408319368958473,
306
+ "num_tokens": 517799.0,
307
+ "step": 165
308
+ },
309
+ {
310
+ "epoch": 2.7039999999999997,
311
+ "grad_norm": 0.38043487071990967,
312
+ "learning_rate": 4.094075209879789e-07,
313
+ "loss": 0.5942,
314
+ "mean_token_accuracy": 0.8503163874149322,
315
+ "num_tokens": 534446.0,
316
+ "step": 170
317
+ },
318
+ {
319
+ "epoch": 2.784,
320
+ "grad_norm": 0.38836878538131714,
321
+ "learning_rate": 2.0470058747505516e-07,
322
+ "loss": 0.6464,
323
+ "mean_token_accuracy": 0.8419791996479035,
324
+ "num_tokens": 549141.0,
325
+ "step": 175
326
+ },
327
+ {
328
+ "epoch": 2.864,
329
+ "grad_norm": 0.4290372133255005,
330
+ "learning_rate": 6.981262574066395e-08,
331
+ "loss": 0.657,
332
+ "mean_token_accuracy": 0.8399893954396248,
333
+ "num_tokens": 564279.0,
334
+ "step": 180
335
+ },
336
+ {
337
+ "epoch": 2.944,
338
+ "grad_norm": 0.3860047161579132,
339
+ "learning_rate": 5.705090702819993e-09,
340
+ "loss": 0.6336,
341
+ "mean_token_accuracy": 0.8413404822349548,
342
+ "num_tokens": 580854.0,
343
+ "step": 185
344
+ },
345
+ {
346
+ "epoch": 2.96,
347
+ "mean_token_accuracy": 0.8438374027609825,
348
+ "num_tokens": 584098.0,
349
+ "step": 186,
350
+ "total_flos": 4332405321474048.0,
351
+ "train_loss": 0.7900132229251247,
352
+ "train_runtime": 706.4309,
353
+ "train_samples_per_second": 4.247,
354
+ "train_steps_per_second": 0.263
355
+ }
356
+ ],
357
+ "logging_steps": 5,
358
+ "max_steps": 186,
359
+ "num_input_tokens_seen": 0,
360
+ "num_train_epochs": 3,
361
+ "save_steps": 500,
362
+ "stateful_callbacks": {
363
+ "TrainerControl": {
364
+ "args": {
365
+ "should_epoch_stop": false,
366
+ "should_evaluate": false,
367
+ "should_log": false,
368
+ "should_save": true,
369
+ "should_training_stop": true
370
+ },
371
+ "attributes": {}
372
+ }
373
+ },
374
+ "total_flos": 4332405321474048.0,
375
+ "train_batch_size": 2,
376
+ "trial_name": null,
377
+ "trial_params": null
378
+ }