Existance commited on
Commit
718f03e
1 Parent(s): dbb791f

Training in progress, step 750, checkpoint

Browse files
checkpoint-750/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: Qwen/Qwen1.5-4B-Chat
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 0.10.0
checkpoint-750/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
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
+ "k_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
checkpoint-750/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234fd2d557f8ff61018ed165ee4a8d8ebcd0d09573165c11748d5ea8ec534476
3
+ size 26235864
checkpoint-750/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-750/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e300126cb6c08994d46b23e018ce7c2b67102c0ce02613e7de7402c0d342b7
3
+ size 52523514
checkpoint-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facd8faf838df24dc1b8c65491845d86cdc829e93133132024cccae67860063d
3
+ size 14244
checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c829b2a7b27fb0ef113dfe1a7e62cbb57ba405460c789ae724e64cad2234d36
3
+ size 1064
checkpoint-750/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
checkpoint-750/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,471 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.2024943828582764,
3
+ "best_model_checkpoint": "./Qwen2-4B-Chat-hinglish-sft/checkpoint-750",
4
+ "epoch": 2.9791459781529293,
5
+ "eval_steps": 25,
6
+ "global_step": 750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "grad_norm": 1.1830133199691772,
14
+ "learning_rate": 0.00019999629591162656,
15
+ "loss": 4.7862,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "eval_loss": 4.098670482635498,
21
+ "eval_runtime": 4.1063,
22
+ "eval_samples_per_second": 2.679,
23
+ "eval_steps_per_second": 2.679,
24
+ "step": 25
25
+ },
26
+ {
27
+ "epoch": 0.2,
28
+ "grad_norm": 1.0619295835494995,
29
+ "learning_rate": 0.00019932568492674144,
30
+ "loss": 2.9161,
31
+ "step": 50
32
+ },
33
+ {
34
+ "epoch": 0.2,
35
+ "eval_loss": 3.1406357288360596,
36
+ "eval_runtime": 4.0777,
37
+ "eval_samples_per_second": 2.698,
38
+ "eval_steps_per_second": 2.698,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.3,
43
+ "grad_norm": 1.1028335094451904,
44
+ "learning_rate": 0.0001975064532257195,
45
+ "loss": 2.4282,
46
+ "step": 75
47
+ },
48
+ {
49
+ "epoch": 0.3,
50
+ "eval_loss": 2.8003995418548584,
51
+ "eval_runtime": 4.076,
52
+ "eval_samples_per_second": 2.699,
53
+ "eval_steps_per_second": 2.699,
54
+ "step": 75
55
+ },
56
+ {
57
+ "epoch": 0.4,
58
+ "grad_norm": 0.9855464100837708,
59
+ "learning_rate": 0.00019455963874271426,
60
+ "loss": 2.2815,
61
+ "step": 100
62
+ },
63
+ {
64
+ "epoch": 0.4,
65
+ "eval_loss": 2.6393470764160156,
66
+ "eval_runtime": 4.084,
67
+ "eval_samples_per_second": 2.693,
68
+ "eval_steps_per_second": 2.693,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.5,
73
+ "grad_norm": 1.154259204864502,
74
+ "learning_rate": 0.00019051931898913976,
75
+ "loss": 2.1485,
76
+ "step": 125
77
+ },
78
+ {
79
+ "epoch": 0.5,
80
+ "eval_loss": 2.5862808227539062,
81
+ "eval_runtime": 4.0324,
82
+ "eval_samples_per_second": 2.728,
83
+ "eval_steps_per_second": 2.728,
84
+ "step": 125
85
+ },
86
+ {
87
+ "epoch": 0.6,
88
+ "grad_norm": 1.2115691900253296,
89
+ "learning_rate": 0.0001854322169749827,
90
+ "loss": 2.0884,
91
+ "step": 150
92
+ },
93
+ {
94
+ "epoch": 0.6,
95
+ "eval_loss": 2.491671323776245,
96
+ "eval_runtime": 4.0837,
97
+ "eval_samples_per_second": 2.694,
98
+ "eval_steps_per_second": 2.694,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.7,
103
+ "grad_norm": 1.0713191032409668,
104
+ "learning_rate": 0.00017935716089521474,
105
+ "loss": 2.1055,
106
+ "step": 175
107
+ },
108
+ {
109
+ "epoch": 0.7,
110
+ "eval_loss": 2.4541499614715576,
111
+ "eval_runtime": 4.0493,
112
+ "eval_samples_per_second": 2.717,
113
+ "eval_steps_per_second": 2.717,
114
+ "step": 175
115
+ },
116
+ {
117
+ "epoch": 0.79,
118
+ "grad_norm": 1.1404445171356201,
119
+ "learning_rate": 0.00017236440382959126,
120
+ "loss": 2.1012,
121
+ "step": 200
122
+ },
123
+ {
124
+ "epoch": 0.79,
125
+ "eval_loss": 2.42814040184021,
126
+ "eval_runtime": 4.0309,
127
+ "eval_samples_per_second": 2.729,
128
+ "eval_steps_per_second": 2.729,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.89,
133
+ "grad_norm": 1.1801480054855347,
134
+ "learning_rate": 0.00016453481132295506,
135
+ "loss": 1.9956,
136
+ "step": 225
137
+ },
138
+ {
139
+ "epoch": 0.89,
140
+ "eval_loss": 2.3967058658599854,
141
+ "eval_runtime": 4.0145,
142
+ "eval_samples_per_second": 2.74,
143
+ "eval_steps_per_second": 2.74,
144
+ "step": 225
145
+ },
146
+ {
147
+ "epoch": 0.99,
148
+ "grad_norm": 1.2651640176773071,
149
+ "learning_rate": 0.00015595892624101765,
150
+ "loss": 1.9931,
151
+ "step": 250
152
+ },
153
+ {
154
+ "epoch": 0.99,
155
+ "eval_loss": 2.3804991245269775,
156
+ "eval_runtime": 4.0509,
157
+ "eval_samples_per_second": 2.715,
158
+ "eval_steps_per_second": 2.715,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 1.09,
163
+ "grad_norm": 1.2018358707427979,
164
+ "learning_rate": 0.00014673592171580025,
165
+ "loss": 1.7605,
166
+ "step": 275
167
+ },
168
+ {
169
+ "epoch": 1.09,
170
+ "eval_loss": 2.358070135116577,
171
+ "eval_runtime": 4.0302,
172
+ "eval_samples_per_second": 2.729,
173
+ "eval_steps_per_second": 2.729,
174
+ "step": 275
175
+ },
176
+ {
177
+ "epoch": 1.19,
178
+ "grad_norm": 1.2622418403625488,
179
+ "learning_rate": 0.00013697245428906732,
180
+ "loss": 1.9231,
181
+ "step": 300
182
+ },
183
+ {
184
+ "epoch": 1.19,
185
+ "eval_loss": 2.3286843299865723,
186
+ "eval_runtime": 4.0327,
187
+ "eval_samples_per_second": 2.728,
188
+ "eval_steps_per_second": 2.728,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 1.29,
193
+ "grad_norm": 1.324831247329712,
194
+ "learning_rate": 0.00012678143051621742,
195
+ "loss": 1.8805,
196
+ "step": 325
197
+ },
198
+ {
199
+ "epoch": 1.29,
200
+ "eval_loss": 2.3032760620117188,
201
+ "eval_runtime": 4.0494,
202
+ "eval_samples_per_second": 2.716,
203
+ "eval_steps_per_second": 2.716,
204
+ "step": 325
205
+ },
206
+ {
207
+ "epoch": 1.39,
208
+ "grad_norm": 1.242129921913147,
209
+ "learning_rate": 0.00011628070129385169,
210
+ "loss": 1.8475,
211
+ "step": 350
212
+ },
213
+ {
214
+ "epoch": 1.39,
215
+ "eval_loss": 2.2904257774353027,
216
+ "eval_runtime": 4.0806,
217
+ "eval_samples_per_second": 2.696,
218
+ "eval_steps_per_second": 2.696,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 1.49,
223
+ "grad_norm": 1.2501651048660278,
224
+ "learning_rate": 0.00010559169901006034,
225
+ "loss": 1.8282,
226
+ "step": 375
227
+ },
228
+ {
229
+ "epoch": 1.49,
230
+ "eval_loss": 2.2831265926361084,
231
+ "eval_runtime": 4.0586,
232
+ "eval_samples_per_second": 2.71,
233
+ "eval_steps_per_second": 2.71,
234
+ "step": 375
235
+ },
236
+ {
237
+ "epoch": 1.59,
238
+ "grad_norm": 1.2264453172683716,
239
+ "learning_rate": 9.483803327767462e-05,
240
+ "loss": 1.8311,
241
+ "step": 400
242
+ },
243
+ {
244
+ "epoch": 1.59,
245
+ "eval_loss": 2.2586615085601807,
246
+ "eval_runtime": 4.0884,
247
+ "eval_samples_per_second": 2.691,
248
+ "eval_steps_per_second": 2.691,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.69,
253
+ "grad_norm": 1.2421507835388184,
254
+ "learning_rate": 8.414406148968657e-05,
255
+ "loss": 1.8051,
256
+ "step": 425
257
+ },
258
+ {
259
+ "epoch": 1.69,
260
+ "eval_loss": 2.2608296871185303,
261
+ "eval_runtime": 4.0277,
262
+ "eval_samples_per_second": 2.731,
263
+ "eval_steps_per_second": 2.731,
264
+ "step": 425
265
+ },
266
+ {
267
+ "epoch": 1.79,
268
+ "grad_norm": 1.4312422275543213,
269
+ "learning_rate": 7.363345072719929e-05,
270
+ "loss": 1.8093,
271
+ "step": 450
272
+ },
273
+ {
274
+ "epoch": 1.79,
275
+ "eval_loss": 2.249046564102173,
276
+ "eval_runtime": 4.1182,
277
+ "eval_samples_per_second": 2.671,
278
+ "eval_steps_per_second": 2.671,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 1.89,
283
+ "grad_norm": 1.3606431484222412,
284
+ "learning_rate": 6.342774765027309e-05,
285
+ "loss": 1.6944,
286
+ "step": 475
287
+ },
288
+ {
289
+ "epoch": 1.89,
290
+ "eval_loss": 2.2398183345794678,
291
+ "eval_runtime": 4.0501,
292
+ "eval_samples_per_second": 2.716,
293
+ "eval_steps_per_second": 2.716,
294
+ "step": 475
295
+ },
296
+ {
297
+ "epoch": 1.99,
298
+ "grad_norm": 1.4951516389846802,
299
+ "learning_rate": 5.3644972909714906e-05,
300
+ "loss": 1.7418,
301
+ "step": 500
302
+ },
303
+ {
304
+ "epoch": 1.99,
305
+ "eval_loss": 2.2147467136383057,
306
+ "eval_runtime": 4.0963,
307
+ "eval_samples_per_second": 2.685,
308
+ "eval_steps_per_second": 2.685,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 2.09,
313
+ "grad_norm": 1.3656489849090576,
314
+ "learning_rate": 4.439825633429557e-05,
315
+ "loss": 1.741,
316
+ "step": 525
317
+ },
318
+ {
319
+ "epoch": 2.09,
320
+ "eval_loss": 2.20865797996521,
321
+ "eval_runtime": 4.08,
322
+ "eval_samples_per_second": 2.696,
323
+ "eval_steps_per_second": 2.696,
324
+ "step": 525
325
+ },
326
+ {
327
+ "epoch": 2.18,
328
+ "grad_norm": 1.3683630228042603,
329
+ "learning_rate": 3.579452867634364e-05,
330
+ "loss": 1.6561,
331
+ "step": 550
332
+ },
333
+ {
334
+ "epoch": 2.18,
335
+ "eval_loss": 2.2086095809936523,
336
+ "eval_runtime": 4.0702,
337
+ "eval_samples_per_second": 2.703,
338
+ "eval_steps_per_second": 2.703,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 2.28,
343
+ "grad_norm": 1.668961524963379,
344
+ "learning_rate": 2.793328504461391e-05,
345
+ "loss": 1.6894,
346
+ "step": 575
347
+ },
348
+ {
349
+ "epoch": 2.28,
350
+ "eval_loss": 2.2114932537078857,
351
+ "eval_runtime": 4.085,
352
+ "eval_samples_per_second": 2.693,
353
+ "eval_steps_per_second": 2.693,
354
+ "step": 575
355
+ },
356
+ {
357
+ "epoch": 2.38,
358
+ "grad_norm": 1.3654729127883911,
359
+ "learning_rate": 2.0905434324322283e-05,
360
+ "loss": 1.5617,
361
+ "step": 600
362
+ },
363
+ {
364
+ "epoch": 2.38,
365
+ "eval_loss": 2.2105047702789307,
366
+ "eval_runtime": 4.0226,
367
+ "eval_samples_per_second": 2.735,
368
+ "eval_steps_per_second": 2.735,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 2.48,
373
+ "grad_norm": 1.1611803770065308,
374
+ "learning_rate": 1.4792247889869071e-05,
375
+ "loss": 1.6809,
376
+ "step": 625
377
+ },
378
+ {
379
+ "epoch": 2.48,
380
+ "eval_loss": 2.2049694061279297,
381
+ "eval_runtime": 4.0427,
382
+ "eval_samples_per_second": 2.721,
383
+ "eval_steps_per_second": 2.721,
384
+ "step": 625
385
+ },
386
+ {
387
+ "epoch": 2.58,
388
+ "grad_norm": 1.6043980121612549,
389
+ "learning_rate": 9.664419767531564e-06,
390
+ "loss": 1.7355,
391
+ "step": 650
392
+ },
393
+ {
394
+ "epoch": 2.58,
395
+ "eval_loss": 2.2034003734588623,
396
+ "eval_runtime": 4.0162,
397
+ "eval_samples_per_second": 2.739,
398
+ "eval_steps_per_second": 2.739,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 2.68,
403
+ "grad_norm": 1.660874843597412,
404
+ "learning_rate": 5.5812491165800675e-06,
405
+ "loss": 1.595,
406
+ "step": 675
407
+ },
408
+ {
409
+ "epoch": 2.68,
410
+ "eval_loss": 2.2044949531555176,
411
+ "eval_runtime": 4.0854,
412
+ "eval_samples_per_second": 2.693,
413
+ "eval_steps_per_second": 2.693,
414
+ "step": 675
415
+ },
416
+ {
417
+ "epoch": 2.78,
418
+ "grad_norm": 1.597719430923462,
419
+ "learning_rate": 2.58995448275795e-06,
420
+ "loss": 1.6264,
421
+ "step": 700
422
+ },
423
+ {
424
+ "epoch": 2.78,
425
+ "eval_loss": 2.203244924545288,
426
+ "eval_runtime": 4.0166,
427
+ "eval_samples_per_second": 2.739,
428
+ "eval_steps_per_second": 2.739,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 2.88,
433
+ "grad_norm": 1.3414063453674316,
434
+ "learning_rate": 7.251277542259849e-07,
435
+ "loss": 1.6195,
436
+ "step": 725
437
+ },
438
+ {
439
+ "epoch": 2.88,
440
+ "eval_loss": 2.2025506496429443,
441
+ "eval_runtime": 4.0553,
442
+ "eval_samples_per_second": 2.712,
443
+ "eval_steps_per_second": 2.712,
444
+ "step": 725
445
+ },
446
+ {
447
+ "epoch": 2.98,
448
+ "grad_norm": 1.5819138288497925,
449
+ "learning_rate": 8.334134526211124e-09,
450
+ "loss": 1.5556,
451
+ "step": 750
452
+ },
453
+ {
454
+ "epoch": 2.98,
455
+ "eval_loss": 2.2024943828582764,
456
+ "eval_runtime": 4.0737,
457
+ "eval_samples_per_second": 2.7,
458
+ "eval_steps_per_second": 2.7,
459
+ "step": 750
460
+ }
461
+ ],
462
+ "logging_steps": 25,
463
+ "max_steps": 753,
464
+ "num_input_tokens_seen": 0,
465
+ "num_train_epochs": 3,
466
+ "save_steps": 25,
467
+ "total_flos": 5355974746460160.0,
468
+ "train_batch_size": 1,
469
+ "trial_name": null,
470
+ "trial_params": null
471
+ }
checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788436dae15eaa59cb0aad969fe709cabdaa4997e955ddb605dac6d71d60cdac
3
+ size 5048
checkpoint-750/vocab.json ADDED
The diff for this file is too large to render. See raw diff