blur0b0t commited on
Commit
c3afa9b
β€’
1 Parent(s): 4d226b4

Upload folder using huggingface_hub

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be94a4f0f91667bca6db4128038f7aef8c95cf882def6649f583e59bc60e1197
3
  size 544841648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8cb1b7f478b3f1162c568eaacec794bbbda87c97dc7ecbd0b0bb55b88beafa
3
  size 544841648
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 4.0,
3
- "total_flos": 176151436984320.0,
4
- "train_loss": 1.4319358553205217,
5
- "train_runtime": 18.7907,
6
- "train_samples": 13,
7
- "train_samples_per_second": 2.767,
8
- "train_steps_per_second": 1.49
9
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "total_flos": 3.551619884777472e+16,
4
+ "train_loss": 0.801731087729141,
5
+ "train_runtime": 3202.2645,
6
+ "train_samples": 2613,
7
+ "train_samples_per_second": 3.264,
8
+ "train_steps_per_second": 1.633
9
  }
{checkpoint-28 β†’ checkpoint-5000}/README.md RENAMED
File without changes
{checkpoint-28 β†’ checkpoint-5000}/adapter_config.json RENAMED
File without changes
{checkpoint-28 β†’ checkpoint-5000}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be94a4f0f91667bca6db4128038f7aef8c95cf882def6649f583e59bc60e1197
3
  size 544841648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c0d2cef7b01e2e2fcbc0316985aaaaf01f8b97395668c749895c501518a449
3
  size 544841648
{checkpoint-28 β†’ checkpoint-5000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:237484bf2ac3f65aafcb20b5743bf6bd3c1c1319966528a7bb64e50db8fa0b9e
3
  size 37990394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a6ef226fa286221fc3f72b2fb8aebe7e62cf574f7a3044f631f07b526711c2
3
  size 37990394
{checkpoint-28 β†’ checkpoint-5000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec7e2b5a6196fca337c8bbaa2e63ce336abdbdbf731991872374ab9a46a8bc68
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3d3cf2c902e0610827e446108ac632ab9869a70055760c6c41bf09f33c25c1
3
  size 14244
{checkpoint-28 β†’ checkpoint-5000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4ca939c39349627ebbc4f461efada993c34387eeab65975e53a7d0b481e126f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1ba951a3f17b4ac4b60e9325a788bb9a7a7e583fa728251aa238398c6dc66d
3
  size 1064
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.8255547054322876,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7651109410864575,
13
+ "grad_norm": 2.158221483230591,
14
+ "learning_rate": 8.337605994872807e-07,
15
+ "loss": 1.2573,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 1.5302218821729152,
20
+ "grad_norm": 2.2398524284362793,
21
+ "learning_rate": 6.365608361269966e-07,
22
+ "loss": 0.9101,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 2.295332823259373,
27
+ "grad_norm": 1.444738507270813,
28
+ "learning_rate": 4.3936107276671263e-07,
29
+ "loss": 0.7317,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 3.06044376434583,
34
+ "grad_norm": 1.4855622053146362,
35
+ "learning_rate": 2.421613094064287e-07,
36
+ "loss": 0.6212,
37
+ "step": 4000
38
+ },
39
+ {
40
+ "epoch": 3.8255547054322876,
41
+ "grad_norm": 2.0333640575408936,
42
+ "learning_rate": 4.4961546046144744e-08,
43
+ "loss": 0.5799,
44
+ "step": 5000
45
+ }
46
+ ],
47
+ "logging_steps": 1000,
48
+ "max_steps": 5228,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 4,
51
+ "save_steps": 1000,
52
+ "stateful_callbacks": {
53
+ "TrainerControl": {
54
+ "args": {
55
+ "should_epoch_stop": false,
56
+ "should_evaluate": false,
57
+ "should_log": false,
58
+ "should_save": true,
59
+ "should_training_stop": false
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 3.397166128594944e+16,
65
+ "train_batch_size": 2,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
{checkpoint-28 β†’ checkpoint-5000}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:549593ec5b76b01321942e2c0be40fcd8f7e50aa46e4f65e9f5f1142a0b11996
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44cd3c0bbdfd294377644249b74e963378130fe594b1ff91d44e99290e66b88
3
  size 5304
checkpoint-5228/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/flan-t5-xl
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 0.9.0
checkpoint-5228/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/flan-t5-xl",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q",
23
+ "v"
24
+ ],
25
+ "task_type": "SEQ_2_SEQ_LM",
26
+ "use_dora": false,
27
+ "use_rslora": false
28
+ }
checkpoint-5228/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8cb1b7f478b3f1162c568eaacec794bbbda87c97dc7ecbd0b0bb55b88beafa
3
+ size 544841648
checkpoint-5228/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41d07b183736dec3fc6e5734e5d74642afbf3d67ec6ff6186a518dd0c158901
3
+ size 37990394
checkpoint-5228/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213c91bf46374887cf60c732956b5f92721324cb72eaf839c3b0d66538a580fe
3
+ size 14244
runs/Jul19_09-49-44_66ad4b953a94/events.out.tfevents.1721383155.66ad4b953a94.193.0 β†’ checkpoint-5228/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e99c71976cfe4b329eb9fbe8d2bb1d0aec735ccdef664688379b78e96f272602
3
- size 6253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37674dec2d637bf9ef2346da110360c6c5b445fd074c64bf85ac1e369e26a3b1
3
+ size 1064
{checkpoint-28 β†’ checkpoint-5228}/trainer_state.json RENAMED
@@ -3,13 +3,49 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 4.0,
5
  "eval_steps": 500,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
- "log_history": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "logging_steps": 1000,
12
- "max_steps": 28,
13
  "num_input_tokens_seen": 0,
14
  "num_train_epochs": 4,
15
  "save_steps": 1000,
@@ -25,7 +61,7 @@
25
  "attributes": {}
26
  }
27
  },
28
- "total_flos": 176151436984320.0,
29
  "train_batch_size": 2,
30
  "trial_name": null,
31
  "trial_params": null
 
3
  "best_model_checkpoint": null,
4
  "epoch": 4.0,
5
  "eval_steps": 500,
6
+ "global_step": 5228,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7651109410864575,
13
+ "grad_norm": 2.158221483230591,
14
+ "learning_rate": 8.337605994872807e-07,
15
+ "loss": 1.2573,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 1.5302218821729152,
20
+ "grad_norm": 2.2398524284362793,
21
+ "learning_rate": 6.365608361269966e-07,
22
+ "loss": 0.9101,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 2.295332823259373,
27
+ "grad_norm": 1.444738507270813,
28
+ "learning_rate": 4.3936107276671263e-07,
29
+ "loss": 0.7317,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 3.06044376434583,
34
+ "grad_norm": 1.4855622053146362,
35
+ "learning_rate": 2.421613094064287e-07,
36
+ "loss": 0.6212,
37
+ "step": 4000
38
+ },
39
+ {
40
+ "epoch": 3.8255547054322876,
41
+ "grad_norm": 2.0333640575408936,
42
+ "learning_rate": 4.4961546046144744e-08,
43
+ "loss": 0.5799,
44
+ "step": 5000
45
+ }
46
+ ],
47
  "logging_steps": 1000,
48
+ "max_steps": 5228,
49
  "num_input_tokens_seen": 0,
50
  "num_train_epochs": 4,
51
  "save_steps": 1000,
 
61
  "attributes": {}
62
  }
63
  },
64
+ "total_flos": 3.551619884777472e+16,
65
  "train_batch_size": 2,
66
  "trial_name": null,
67
  "trial_params": null
checkpoint-5228/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44cd3c0bbdfd294377644249b74e963378130fe594b1ff91d44e99290e66b88
3
+ size 5304
runs/Jul19_10-44-41_6a32a2c667bd/events.out.tfevents.1721385983.6a32a2c667bd.133.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438b32ebc9b059995af8b3cb3383a85f32b1f44aa052ed7cecbbf564f4cffeff
3
+ size 7345
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 256,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 4.0,
3
- "total_flos": 176151436984320.0,
4
- "train_loss": 1.4319358553205217,
5
- "train_runtime": 18.7907,
6
- "train_samples": 13,
7
- "train_samples_per_second": 2.767,
8
- "train_steps_per_second": 1.49
9
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "total_flos": 3.551619884777472e+16,
4
+ "train_loss": 0.801731087729141,
5
+ "train_runtime": 3202.2645,
6
+ "train_samples": 2613,
7
+ "train_samples_per_second": 3.264,
8
+ "train_steps_per_second": 1.633
9
  }
trainer_state.json CHANGED
@@ -3,23 +3,58 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 4.0,
5
  "eval_steps": 500,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  {
12
  "epoch": 4.0,
13
- "step": 28,
14
- "total_flos": 176151436984320.0,
15
- "train_loss": 1.4319358553205217,
16
- "train_runtime": 18.7907,
17
- "train_samples_per_second": 2.767,
18
- "train_steps_per_second": 1.49
19
  }
20
  ],
21
  "logging_steps": 1000,
22
- "max_steps": 28,
23
  "num_input_tokens_seen": 0,
24
  "num_train_epochs": 4,
25
  "save_steps": 1000,
@@ -35,7 +70,7 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 176151436984320.0,
39
  "train_batch_size": 2,
40
  "trial_name": null,
41
  "trial_params": null
 
3
  "best_model_checkpoint": null,
4
  "epoch": 4.0,
5
  "eval_steps": 500,
6
+ "global_step": 5228,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
+ {
12
+ "epoch": 0.7651109410864575,
13
+ "grad_norm": 2.158221483230591,
14
+ "learning_rate": 8.337605994872807e-07,
15
+ "loss": 1.2573,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 1.5302218821729152,
20
+ "grad_norm": 2.2398524284362793,
21
+ "learning_rate": 6.365608361269966e-07,
22
+ "loss": 0.9101,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 2.295332823259373,
27
+ "grad_norm": 1.444738507270813,
28
+ "learning_rate": 4.3936107276671263e-07,
29
+ "loss": 0.7317,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 3.06044376434583,
34
+ "grad_norm": 1.4855622053146362,
35
+ "learning_rate": 2.421613094064287e-07,
36
+ "loss": 0.6212,
37
+ "step": 4000
38
+ },
39
+ {
40
+ "epoch": 3.8255547054322876,
41
+ "grad_norm": 2.0333640575408936,
42
+ "learning_rate": 4.4961546046144744e-08,
43
+ "loss": 0.5799,
44
+ "step": 5000
45
+ },
46
  {
47
  "epoch": 4.0,
48
+ "step": 5228,
49
+ "total_flos": 3.551619884777472e+16,
50
+ "train_loss": 0.801731087729141,
51
+ "train_runtime": 3202.2645,
52
+ "train_samples_per_second": 3.264,
53
+ "train_steps_per_second": 1.633
54
  }
55
  ],
56
  "logging_steps": 1000,
57
+ "max_steps": 5228,
58
  "num_input_tokens_seen": 0,
59
  "num_train_epochs": 4,
60
  "save_steps": 1000,
 
70
  "attributes": {}
71
  }
72
  },
73
+ "total_flos": 3.551619884777472e+16,
74
  "train_batch_size": 2,
75
  "trial_name": null,
76
  "trial_params": null