Hugging Face's logo

trl-lib
/
qwen1.5-1.8b-sft

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
alignment-handbook
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
lewtun HF Staff commited on
Commit
6eac95c
·
verified ·
1 Parent(s): e3b2ce4

Add HuggingFaceH4/qwen-1.5-1.8b-sft-v0.0 checkpoint

Browse files
Files changed (22) hide show
  1. README.md +67 -0
  2. added_tokens.json +5 -0
  3. all_results.json +14 -0
  4. config.json +28 -0
  5. eval_results.json +9 -0
  6. generation_config.json +6 -0
  7. merges.txt +0 -0
  8. model.safetensors +3 -0
  9. runs/Mar13_15-55-26_ip-26-0-167-175/events.out.tfevents.1710345414.ip-26-0-167-175.47301.0 +3 -0
  10. runs/Mar13_16-10-47_ip-26-0-167-175/events.out.tfevents.1710346278.ip-26-0-167-175.49847.0 +3 -0
  11. runs/Mar13_16-17-22_ip-26-0-167-175/events.out.tfevents.1710346695.ip-26-0-167-175.50976.0 +3 -0
  12. runs/Mar13_16-33-16_ip-26-0-167-175/events.out.tfevents.1710347631.ip-26-0-167-175.54812.0 +3 -0
  13. runs/Mar13_16-35-17_ip-26-0-167-175/events.out.tfevents.1710347746.ip-26-0-167-175.55966.0 +3 -0
  14. runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710354517.ip-26-0-166-244.384933.0 +3 -0
  15. runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710355686.ip-26-0-166-244.384933.1 +3 -0
  16. special_tokens_map.json +21 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +43 -0
  19. train_results.json +8 -0
  20. trainer_state.json +1055 -0
  21. training_args.bin +3 -0
  22. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: Qwen/Qwen1.5-1.8B
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - HuggingFaceH4/deita-6k-v0-sft
9
+ model-index:
10
+ - name: qwen-1.5-1.8b-sft-v0.0
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # qwen-1.5-1.8b-sft-v0.0
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the HuggingFaceH4/deita-6k-v0-sft dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.0886
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 8
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 64
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 3
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 1.0963 | 1.0 | 237 | 1.0788 |
58
+ | 0.9779 | 2.0 | 474 | 1.0728 |
59
+ | 0.8734 | 3.0 | 711 | 1.0886 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.38.2
65
+ - Pytorch 2.1.2+cu121
66
+ - Datasets 2.16.1
67
+ - Tokenizers 0.15.1
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.0886437892913818,
4
+ "eval_runtime": 4.9902,
5
+ "eval_samples": 300,
6
+ "eval_samples_per_second": 295.379,
7
+ "eval_steps_per_second": 4.809,
8
+ "perplexity": 2.970243064281644,
9
+ "train_loss": 0.9885472514458347,
10
+ "train_runtime": 1164.5291,
11
+ "train_samples": 5700,
12
+ "train_samples_per_second": 77.885,
13
+ "train_steps_per_second": 0.611
14
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-1.8B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 5504,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.38.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151648
28
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.0886437892913818,
4
+ "eval_runtime": 4.9902,
5
+ "eval_samples": 300,
6
+ "eval_samples_per_second": 295.379,
7
+ "eval_steps_per_second": 4.809,
8
+ "perplexity": 2.970243064281644
9
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.38.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0528c447ff8ef58d7e4b75f6dffdc118c7e6265f71cba9d51f5f82568116307
3
+ size 3671331400
runs/Mar13_15-55-26_ip-26-0-167-175/events.out.tfevents.1710345414.ip-26-0-167-175.47301.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcbb00e9e4a6f8a9cff3001a39152ae4220f2a3ba65b4ed36428d04b9a238ae
3
+ size 5110
runs/Mar13_16-10-47_ip-26-0-167-175/events.out.tfevents.1710346278.ip-26-0-167-175.49847.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167ac8274f99fda2d60119233034cad0bbe44b2aeb1f55df903356b9394d257d
3
+ size 5110
runs/Mar13_16-17-22_ip-26-0-167-175/events.out.tfevents.1710346695.ip-26-0-167-175.50976.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a971f7d2d93ef149c56b264a95b1fe506e03c9a211259843b5e59aa52e9921
3
+ size 5317
runs/Mar13_16-33-16_ip-26-0-167-175/events.out.tfevents.1710347631.ip-26-0-167-175.54812.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becc4d3160a74d30ac97faae40040b5977547de2d0e8779c770127e2151d21df
3
+ size 5105
runs/Mar13_16-35-17_ip-26-0-167-175/events.out.tfevents.1710347746.ip-26-0-167-175.55966.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b941c9b2a5ddf02dc52346adf9c57b72e773e694d4cc30cb6046a3805a3d698
3
+ size 5519
runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710354517.ip-26-0-166-244.384933.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c12ca5f508bfce039e6123ea4eb46789c5bb749ec484f8831905745ee75c78c
3
+ size 36317
runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710355686.ip-26-0-166-244.384933.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad5e4f6ab8854be1b807b29c827115dab39773081d73145e925d633d9817241
3
+ size 359
special_tokens_map.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>"
21
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "<|im_start|>",
34
+ "chat_template": "{% for message in messages %}{{'<|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": "<|im_end|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.9885472514458347,
4
+ "train_runtime": 1164.5291,
5
+ "train_samples": 5700,
6
+ "train_samples_per_second": 77.885,
7
+ "train_steps_per_second": 0.611
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1055 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 711,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 6.304776350824905,
14
+ "learning_rate": 2.7777777777777776e-07,
15
+ "loss": 1.2835,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 6.1444154892612906,
21
+ "learning_rate": 1.3888888888888892e-06,
22
+ "loss": 1.2052,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.04,
27
+ "grad_norm": 3.829285889985009,
28
+ "learning_rate": 2.7777777777777783e-06,
29
+ "loss": 1.2292,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.06,
34
+ "grad_norm": 1.1679705762984034,
35
+ "learning_rate": 4.166666666666667e-06,
36
+ "loss": 1.1597,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.08,
41
+ "grad_norm": 1.4357027628580525,
42
+ "learning_rate": 5.555555555555557e-06,
43
+ "loss": 1.1284,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.11,
48
+ "grad_norm": 0.9452863213714234,
49
+ "learning_rate": 6.944444444444445e-06,
50
+ "loss": 1.1531,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.13,
55
+ "grad_norm": 0.8873033736663324,
56
+ "learning_rate": 8.333333333333334e-06,
57
+ "loss": 1.1549,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.15,
62
+ "grad_norm": 0.7881640401882983,
63
+ "learning_rate": 9.722222222222223e-06,
64
+ "loss": 1.1306,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.17,
69
+ "grad_norm": 0.7249086340452754,
70
+ "learning_rate": 1.1111111111111113e-05,
71
+ "loss": 1.0851,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.19,
76
+ "grad_norm": 0.6764364880756644,
77
+ "learning_rate": 1.25e-05,
78
+ "loss": 1.139,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.21,
83
+ "grad_norm": 0.6897544761050797,
84
+ "learning_rate": 1.388888888888889e-05,
85
+ "loss": 1.1317,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.23,
90
+ "grad_norm": 0.6816142474216428,
91
+ "learning_rate": 1.5277777777777777e-05,
92
+ "loss": 1.1313,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.25,
97
+ "grad_norm": 0.6811212493739357,
98
+ "learning_rate": 1.6666666666666667e-05,
99
+ "loss": 1.138,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.27,
104
+ "grad_norm": 0.6862844341255663,
105
+ "learning_rate": 1.8055555555555558e-05,
106
+ "loss": 1.1483,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.3,
111
+ "grad_norm": 1.4787128965985026,
112
+ "learning_rate": 1.9444444444444445e-05,
113
+ "loss": 1.1395,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.32,
118
+ "grad_norm": 0.7775487986058592,
119
+ "learning_rate": 1.999891231617599e-05,
120
+ "loss": 1.1161,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.34,
125
+ "grad_norm": 0.7115088691454458,
126
+ "learning_rate": 1.9992266216318037e-05,
127
+ "loss": 1.0932,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "grad_norm": 0.6818793389006765,
133
+ "learning_rate": 1.997958229642588e-05,
134
+ "loss": 1.1178,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.38,
139
+ "grad_norm": 0.6928106880338162,
140
+ "learning_rate": 1.996086822074945e-05,
141
+ "loss": 1.1298,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.4,
146
+ "grad_norm": 0.6676196732940871,
147
+ "learning_rate": 1.9936135297256183e-05,
148
+ "loss": 1.1094,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.42,
153
+ "grad_norm": 0.713377771129619,
154
+ "learning_rate": 1.9905398470798207e-05,
155
+ "loss": 1.1224,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.44,
160
+ "grad_norm": 0.6855059849013185,
161
+ "learning_rate": 1.9868676314081907e-05,
162
+ "loss": 1.1123,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.46,
167
+ "grad_norm": 0.660806750689474,
168
+ "learning_rate": 1.9825991016445387e-05,
169
+ "loss": 1.1044,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.49,
174
+ "grad_norm": 0.6638994109236709,
175
+ "learning_rate": 1.9777368370450582e-05,
176
+ "loss": 1.0811,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.51,
181
+ "grad_norm": 0.6862841124125318,
182
+ "learning_rate": 1.9722837756298112e-05,
183
+ "loss": 1.1057,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.53,
188
+ "grad_norm": 0.6713561495513073,
189
+ "learning_rate": 1.9662432124074325e-05,
190
+ "loss": 1.1247,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.55,
195
+ "grad_norm": 0.6865654618803174,
196
+ "learning_rate": 1.9596187973841218e-05,
197
+ "loss": 1.0959,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.57,
202
+ "grad_norm": 0.6512909442458682,
203
+ "learning_rate": 1.9524145333581315e-05,
204
+ "loss": 1.1178,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.59,
209
+ "grad_norm": 1.542422418836288,
210
+ "learning_rate": 1.9446347735010765e-05,
211
+ "loss": 1.0984,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.61,
216
+ "grad_norm": 0.7206951642675766,
217
+ "learning_rate": 1.9362842187275354e-05,
218
+ "loss": 1.0812,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.63,
223
+ "grad_norm": 0.6984462641482525,
224
+ "learning_rate": 1.9273679148545246e-05,
225
+ "loss": 1.1129,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.65,
230
+ "grad_norm": 0.6657063460800421,
231
+ "learning_rate": 1.917891249552568e-05,
232
+ "loss": 1.1147,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.68,
237
+ "grad_norm": 0.6732684805189473,
238
+ "learning_rate": 1.9078599490901984e-05,
239
+ "loss": 1.0988,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.7,
244
+ "grad_norm": 0.6969660113279658,
245
+ "learning_rate": 1.897280074873868e-05,
246
+ "loss": 1.0901,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.72,
251
+ "grad_norm": 0.6545636951842201,
252
+ "learning_rate": 1.8861580197853423e-05,
253
+ "loss": 1.0808,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.74,
258
+ "grad_norm": 0.728879426031119,
259
+ "learning_rate": 1.8745005043188104e-05,
260
+ "loss": 1.1007,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.76,
265
+ "grad_norm": 0.6989476047236611,
266
+ "learning_rate": 1.862314572520028e-05,
267
+ "loss": 1.0972,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.78,
272
+ "grad_norm": 0.6937493330837292,
273
+ "learning_rate": 1.8496075877299585e-05,
274
+ "loss": 1.0751,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.8,
279
+ "grad_norm": 0.7237715465824409,
280
+ "learning_rate": 1.8363872281354796e-05,
281
+ "loss": 1.1005,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.82,
286
+ "grad_norm": 0.665001160804127,
287
+ "learning_rate": 1.8226614821298444e-05,
288
+ "loss": 1.0979,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.84,
293
+ "grad_norm": 0.6512333420285555,
294
+ "learning_rate": 1.808438643485698e-05,
295
+ "loss": 1.0663,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.86,
300
+ "grad_norm": 0.6670845393437954,
301
+ "learning_rate": 1.793727306343574e-05,
302
+ "loss": 1.0479,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.89,
307
+ "grad_norm": 0.660996369149025,
308
+ "learning_rate": 1.7785363600188894e-05,
309
+ "loss": 1.0631,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.91,
314
+ "grad_norm": 0.6383025721204546,
315
+ "learning_rate": 1.762874983630582e-05,
316
+ "loss": 1.0594,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.93,
321
+ "grad_norm": 0.6481663495293073,
322
+ "learning_rate": 1.7467526405546344e-05,
323
+ "loss": 1.1117,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.95,
328
+ "grad_norm": 0.6526574717781632,
329
+ "learning_rate": 1.7301790727058344e-05,
330
+ "loss": 1.074,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.97,
335
+ "grad_norm": 0.6602485216423672,
336
+ "learning_rate": 1.7131642946512314e-05,
337
+ "loss": 1.1002,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.99,
342
+ "grad_norm": 0.703340110707448,
343
+ "learning_rate": 1.6957185875588403e-05,
344
+ "loss": 1.0963,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 1.0,
349
+ "eval_loss": 1.0788308382034302,
350
+ "eval_runtime": 5.3118,
351
+ "eval_samples_per_second": 277.497,
352
+ "eval_steps_per_second": 4.518,
353
+ "step": 237
354
+ },
355
+ {
356
+ "epoch": 1.01,
357
+ "grad_norm": 0.7492129279971655,
358
+ "learning_rate": 1.6778524929852513e-05,
359
+ "loss": 1.028,
360
+ "step": 240
361
+ },
362
+ {
363
+ "epoch": 1.03,
364
+ "grad_norm": 0.8102380476622988,
365
+ "learning_rate": 1.659576806505905e-05,
366
+ "loss": 0.9794,
367
+ "step": 245
368
+ },
369
+ {
370
+ "epoch": 1.05,
371
+ "grad_norm": 0.7121110613571635,
372
+ "learning_rate": 1.640902571191869e-05,
373
+ "loss": 0.9648,
374
+ "step": 250
375
+ },
376
+ {
377
+ "epoch": 1.08,
378
+ "grad_norm": 0.7426962668349942,
379
+ "learning_rate": 1.6218410709370735e-05,
380
+ "loss": 0.9826,
381
+ "step": 255
382
+ },
383
+ {
384
+ "epoch": 1.1,
385
+ "grad_norm": 0.675584007232439,
386
+ "learning_rate": 1.6024038236400246e-05,
387
+ "loss": 0.9454,
388
+ "step": 260
389
+ },
390
+ {
391
+ "epoch": 1.12,
392
+ "grad_norm": 0.7129690280611058,
393
+ "learning_rate": 1.582602574244121e-05,
394
+ "loss": 0.9403,
395
+ "step": 265
396
+ },
397
+ {
398
+ "epoch": 1.14,
399
+ "grad_norm": 0.6747033998323487,
400
+ "learning_rate": 1.562449287640781e-05,
401
+ "loss": 0.9864,
402
+ "step": 270
403
+ },
404
+ {
405
+ "epoch": 1.16,
406
+ "grad_norm": 0.6837814023465153,
407
+ "learning_rate": 1.5419561414396657e-05,
408
+ "loss": 0.9864,
409
+ "step": 275
410
+ },
411
+ {
412
+ "epoch": 1.18,
413
+ "grad_norm": 0.6969571002742431,
414
+ "learning_rate": 1.5211355186103655e-05,
415
+ "loss": 0.9567,
416
+ "step": 280
417
+ },
418
+ {
419
+ "epoch": 1.2,
420
+ "grad_norm": 0.6630210250243682,
421
+ "learning_rate": 1.5000000000000002e-05,
422
+ "loss": 0.9811,
423
+ "step": 285
424
+ },
425
+ {
426
+ "epoch": 1.22,
427
+ "grad_norm": 0.6589068053142794,
428
+ "learning_rate": 1.4785623567312492e-05,
429
+ "loss": 0.9389,
430
+ "step": 290
431
+ },
432
+ {
433
+ "epoch": 1.24,
434
+ "grad_norm": 0.6878317017661794,
435
+ "learning_rate": 1.4568355424854113e-05,
436
+ "loss": 1.0157,
437
+ "step": 295
438
+ },
439
+ {
440
+ "epoch": 1.27,
441
+ "grad_norm": 0.7179535464777137,
442
+ "learning_rate": 1.4348326856751496e-05,
443
+ "loss": 0.9787,
444
+ "step": 300
445
+ },
446
+ {
447
+ "epoch": 1.29,
448
+ "grad_norm": 0.6829129430840285,
449
+ "learning_rate": 1.412567081511659e-05,
450
+ "loss": 0.9639,
451
+ "step": 305
452
+ },
453
+ {
454
+ "epoch": 1.31,
455
+ "grad_norm": 0.7030815356191583,
456
+ "learning_rate": 1.3900521839710428e-05,
457
+ "loss": 0.9486,
458
+ "step": 310
459
+ },
460
+ {
461
+ "epoch": 1.33,
462
+ "grad_norm": 0.67559393512531,
463
+ "learning_rate": 1.367301597664757e-05,
464
+ "loss": 0.9795,
465
+ "step": 315
466
+ },
467
+ {
468
+ "epoch": 1.35,
469
+ "grad_norm": 0.6780812345565891,
470
+ "learning_rate": 1.3443290696190335e-05,
471
+ "loss": 0.9785,
472
+ "step": 320
473
+ },
474
+ {
475
+ "epoch": 1.37,
476
+ "grad_norm": 0.6710329710920228,
477
+ "learning_rate": 1.3211484809682482e-05,
478
+ "loss": 0.992,
479
+ "step": 325
480
+ },
481
+ {
482
+ "epoch": 1.39,
483
+ "grad_norm": 0.6741452885754833,
484
+ "learning_rate": 1.2977738385672558e-05,
485
+ "loss": 1.0023,
486
+ "step": 330
487
+ },
488
+ {
489
+ "epoch": 1.41,
490
+ "grad_norm": 0.6632729564225439,
491
+ "learning_rate": 1.2742192665277569e-05,
492
+ "loss": 0.995,
493
+ "step": 335
494
+ },
495
+ {
496
+ "epoch": 1.43,
497
+ "grad_norm": 0.6601370650300007,
498
+ "learning_rate": 1.250498997683813e-05,
499
+ "loss": 0.9764,
500
+ "step": 340
501
+ },
502
+ {
503
+ "epoch": 1.46,
504
+ "grad_norm": 0.6652011155656283,
505
+ "learning_rate": 1.2266273649916669e-05,
506
+ "loss": 0.9537,
507
+ "step": 345
508
+ },
509
+ {
510
+ "epoch": 1.48,
511
+ "grad_norm": 0.6446717094616893,
512
+ "learning_rate": 1.202618792869063e-05,
513
+ "loss": 0.9525,
514
+ "step": 350
515
+ },
516
+ {
517
+ "epoch": 1.5,
518
+ "grad_norm": 0.6721085026757567,
519
+ "learning_rate": 1.178487788479303e-05,
520
+ "loss": 0.9629,
521
+ "step": 355
522
+ },
523
+ {
524
+ "epoch": 1.52,
525
+ "grad_norm": 0.6629783449328003,
526
+ "learning_rate": 1.1542489329653024e-05,
527
+ "loss": 0.9842,
528
+ "step": 360
529
+ },
530
+ {
531
+ "epoch": 1.54,
532
+ "grad_norm": 0.6522335344513943,
533
+ "learning_rate": 1.129916872638945e-05,
534
+ "loss": 1.0048,
535
+ "step": 365
536
+ },
537
+ {
538
+ "epoch": 1.56,
539
+ "grad_norm": 0.6781899139396206,
540
+ "learning_rate": 1.1055063101310581e-05,
541
+ "loss": 0.9685,
542
+ "step": 370
543
+ },
544
+ {
545
+ "epoch": 1.58,
546
+ "grad_norm": 0.6691172096591039,
547
+ "learning_rate": 1.08103199550736e-05,
548
+ "loss": 0.9747,
549
+ "step": 375
550
+ },
551
+ {
552
+ "epoch": 1.6,
553
+ "grad_norm": 0.6373869560949246,
554
+ "learning_rate": 1.0565087173557396e-05,
555
+ "loss": 0.9686,
556
+ "step": 380
557
+ },
558
+ {
559
+ "epoch": 1.62,
560
+ "grad_norm": 0.6517373978992131,
561
+ "learning_rate": 1.0319512938502654e-05,
562
+ "loss": 0.9714,
563
+ "step": 385
564
+ },
565
+ {
566
+ "epoch": 1.65,
567
+ "grad_norm": 0.6580577126773488,
568
+ "learning_rate": 1.0073745637973125e-05,
569
+ "loss": 0.9747,
570
+ "step": 390
571
+ },
572
+ {
573
+ "epoch": 1.67,
574
+ "grad_norm": 0.6489932524871953,
575
+ "learning_rate": 9.827933776692236e-06,
576
+ "loss": 0.9874,
577
+ "step": 395
578
+ },
579
+ {
580
+ "epoch": 1.69,
581
+ "grad_norm": 0.6407459560571601,
582
+ "learning_rate": 9.582225886309217e-06,
583
+ "loss": 0.9618,
584
+ "step": 400
585
+ },
586
+ {
587
+ "epoch": 1.71,
588
+ "grad_norm": 0.6629610117016943,
589
+ "learning_rate": 9.336770435648963e-06,
590
+ "loss": 0.992,
591
+ "step": 405
592
+ },
593
+ {
594
+ "epoch": 1.73,
595
+ "grad_norm": 0.6667119859349727,
596
+ "learning_rate": 9.091715740999829e-06,
597
+ "loss": 0.971,
598
+ "step": 410
599
+ },
600
+ {
601
+ "epoch": 1.75,
602
+ "grad_norm": 0.6886862002448931,
603
+ "learning_rate": 8.84720987649363e-06,
604
+ "loss": 0.9556,
605
+ "step": 415
606
+ },
607
+ {
608
+ "epoch": 1.77,
609
+ "grad_norm": 0.6426160780174832,
610
+ "learning_rate": 8.60340058463194e-06,
611
+ "loss": 0.9879,
612
+ "step": 420
613
+ },
614
+ {
615
+ "epoch": 1.79,
616
+ "grad_norm": 0.6346609133677081,
617
+ "learning_rate": 8.360435187012789e-06,
618
+ "loss": 1.0061,
619
+ "step": 425
620
+ },
621
+ {
622
+ "epoch": 1.81,
623
+ "grad_norm": 0.6483257723288812,
624
+ "learning_rate": 8.118460495311687e-06,
625
+ "loss": 1.0141,
626
+ "step": 430
627
+ },
628
+ {
629
+ "epoch": 1.84,
630
+ "grad_norm": 0.7171449794590815,
631
+ "learning_rate": 7.877622722570772e-06,
632
+ "loss": 0.9675,
633
+ "step": 435
634
+ },
635
+ {
636
+ "epoch": 1.86,
637
+ "grad_norm": 0.650114145091982,
638
+ "learning_rate": 7.638067394849672e-06,
639
+ "loss": 0.9742,
640
+ "step": 440
641
+ },
642
+ {
643
+ "epoch": 1.88,
644
+ "grad_norm": 0.6929157157409924,
645
+ "learning_rate": 7.3999392632914936e-06,
646
+ "loss": 0.9872,
647
+ "step": 445
648
+ },
649
+ {
650
+ "epoch": 1.9,
651
+ "grad_norm": 0.6361399427239406,
652
+ "learning_rate": 7.163382216657033e-06,
653
+ "loss": 0.9685,
654
+ "step": 450
655
+ },
656
+ {
657
+ "epoch": 1.92,
658
+ "grad_norm": 0.6216240484506025,
659
+ "learning_rate": 6.928539194380101e-06,
660
+ "loss": 0.9648,
661
+ "step": 455
662
+ },
663
+ {
664
+ "epoch": 1.94,
665
+ "grad_norm": 0.6162980824439727,
666
+ "learning_rate": 6.6955521001964526e-06,
667
+ "loss": 0.9608,
668
+ "step": 460
669
+ },
670
+ {
671
+ "epoch": 1.96,
672
+ "grad_norm": 0.662006443614462,
673
+ "learning_rate": 6.464561716398565e-06,
674
+ "loss": 0.9555,
675
+ "step": 465
676
+ },
677
+ {
678
+ "epoch": 1.98,
679
+ "grad_norm": 0.6525504751262218,
680
+ "learning_rate": 6.2357076187680325e-06,
681
+ "loss": 0.9779,
682
+ "step": 470
683
+ },
684
+ {
685
+ "epoch": 2.0,
686
+ "eval_loss": 1.0727574825286865,
687
+ "eval_runtime": 4.9769,
688
+ "eval_samples_per_second": 296.167,
689
+ "eval_steps_per_second": 4.822,
690
+ "step": 474
691
+ },
692
+ {
693
+ "epoch": 2.0,
694
+ "grad_norm": 0.9211908456070792,
695
+ "learning_rate": 6.009128092236983e-06,
696
+ "loss": 0.9304,
697
+ "step": 475
698
+ },
699
+ {
700
+ "epoch": 2.03,
701
+ "grad_norm": 0.8532374349387694,
702
+ "learning_rate": 5.78496004732952e-06,
703
+ "loss": 0.8546,
704
+ "step": 480
705
+ },
706
+ {
707
+ "epoch": 2.05,
708
+ "grad_norm": 0.7234550887455584,
709
+ "learning_rate": 5.563338937433622e-06,
710
+ "loss": 0.8819,
711
+ "step": 485
712
+ },
713
+ {
714
+ "epoch": 2.07,
715
+ "grad_norm": 0.7126403603814161,
716
+ "learning_rate": 5.344398676953526e-06,
717
+ "loss": 0.9011,
718
+ "step": 490
719
+ },
720
+ {
721
+ "epoch": 2.09,
722
+ "grad_norm": 0.640441506166026,
723
+ "learning_rate": 5.128271560392037e-06,
724
+ "loss": 0.8714,
725
+ "step": 495
726
+ },
727
+ {
728
+ "epoch": 2.11,
729
+ "grad_norm": 0.6599554320566688,
730
+ "learning_rate": 4.915088182411674e-06,
731
+ "loss": 0.8918,
732
+ "step": 500
733
+ },
734
+ {
735
+ "epoch": 2.13,
736
+ "grad_norm": 0.6420656415982475,
737
+ "learning_rate": 4.7049773589229306e-06,
738
+ "loss": 0.8936,
739
+ "step": 505
740
+ },
741
+ {
742
+ "epoch": 2.15,
743
+ "grad_norm": 0.6624281801845274,
744
+ "learning_rate": 4.498066049247344e-06,
745
+ "loss": 0.9076,
746
+ "step": 510
747
+ },
748
+ {
749
+ "epoch": 2.17,
750
+ "grad_norm": 0.6494624453990643,
751
+ "learning_rate": 4.29447927940242e-06,
752
+ "loss": 0.874,
753
+ "step": 515
754
+ },
755
+ {
756
+ "epoch": 2.19,
757
+ "grad_norm": 0.62980438510625,
758
+ "learning_rate": 4.094340066554742e-06,
759
+ "loss": 0.8797,
760
+ "step": 520
761
+ },
762
+ {
763
+ "epoch": 2.22,
764
+ "grad_norm": 0.6496965620768959,
765
+ "learning_rate": 3.897769344686929e-06,
766
+ "loss": 0.8783,
767
+ "step": 525
768
+ },
769
+ {
770
+ "epoch": 2.24,
771
+ "grad_norm": 0.623988823063145,
772
+ "learning_rate": 3.7048858915233665e-06,
773
+ "loss": 0.8991,
774
+ "step": 530
775
+ },
776
+ {
777
+ "epoch": 2.26,
778
+ "grad_norm": 0.6235243813957997,
779
+ "learning_rate": 3.5158062567588468e-06,
780
+ "loss": 0.8587,
781
+ "step": 535
782
+ },
783
+ {
784
+ "epoch": 2.28,
785
+ "grad_norm": 0.6224524258972475,
786
+ "learning_rate": 3.330644691633492e-06,
787
+ "loss": 0.8742,
788
+ "step": 540
789
+ },
790
+ {
791
+ "epoch": 2.3,
792
+ "grad_norm": 0.6267167014433769,
793
+ "learning_rate": 3.149513079896521e-06,
794
+ "loss": 0.9013,
795
+ "step": 545
796
+ },
797
+ {
798
+ "epoch": 2.32,
799
+ "grad_norm": 0.6252594161210878,
800
+ "learning_rate": 2.9725208702005736e-06,
801
+ "loss": 0.8905,
802
+ "step": 550
803
+ },
804
+ {
805
+ "epoch": 2.34,
806
+ "grad_norm": 0.6204178434773648,
807
+ "learning_rate": 2.7997750099674282e-06,
808
+ "loss": 0.8819,
809
+ "step": 555
810
+ },
811
+ {
812
+ "epoch": 2.36,
813
+ "grad_norm": 0.6234939504584522,
814
+ "learning_rate": 2.631379880765107e-06,
815
+ "loss": 0.8844,
816
+ "step": 560
817
+ },
818
+ {
819
+ "epoch": 2.38,
820
+ "grad_norm": 0.6404757813962814,
821
+ "learning_rate": 2.467437235235378e-06,
822
+ "loss": 0.8643,
823
+ "step": 565
824
+ },
825
+ {
826
+ "epoch": 2.41,
827
+ "grad_norm": 0.6154655956232923,
828
+ "learning_rate": 2.3080461356097938e-06,
829
+ "loss": 0.8835,
830
+ "step": 570
831
+ },
832
+ {
833
+ "epoch": 2.43,
834
+ "grad_norm": 0.6226597834743854,
835
+ "learning_rate": 2.153302893851401e-06,
836
+ "loss": 0.8547,
837
+ "step": 575
838
+ },
839
+ {
840
+ "epoch": 2.45,
841
+ "grad_norm": 0.635711672458865,
842
+ "learning_rate": 2.0033010134583085e-06,
843
+ "loss": 0.8799,
844
+ "step": 580
845
+ },
846
+ {
847
+ "epoch": 2.47,
848
+ "grad_norm": 0.6222216060732768,
849
+ "learning_rate": 1.8581311329642592e-06,
850
+ "loss": 0.8614,
851
+ "step": 585
852
+ },
853
+ {
854
+ "epoch": 2.49,
855
+ "grad_norm": 0.6211538083313471,
856
+ "learning_rate": 1.7178809711703525e-06,
857
+ "loss": 0.8851,
858
+ "step": 590
859
+ },
860
+ {
861
+ "epoch": 2.51,
862
+ "grad_norm": 0.6264778347828893,
863
+ "learning_rate": 1.5826352741410333e-06,
864
+ "loss": 0.8841,
865
+ "step": 595
866
+ },
867
+ {
868
+ "epoch": 2.53,
869
+ "grad_norm": 0.6194165165737189,
870
+ "learning_rate": 1.452475763996326e-06,
871
+ "loss": 0.8519,
872
+ "step": 600
873
+ },
874
+ {
875
+ "epoch": 2.55,
876
+ "grad_norm": 0.6156200040809161,
877
+ "learning_rate": 1.3274810895313083e-06,
878
+ "loss": 0.8595,
879
+ "step": 605
880
+ },
881
+ {
882
+ "epoch": 2.57,
883
+ "grad_norm": 0.6268920763538539,
884
+ "learning_rate": 1.207726778692625e-06,
885
+ "loss": 0.8668,
886
+ "step": 610
887
+ },
888
+ {
889
+ "epoch": 2.59,
890
+ "grad_norm": 0.6237602437342175,
891
+ "learning_rate": 1.0932851929407828e-06,
892
+ "loss": 0.8984,
893
+ "step": 615
894
+ },
895
+ {
896
+ "epoch": 2.62,
897
+ "grad_norm": 0.6098041198161336,
898
+ "learning_rate": 9.842254835257792e-07,
899
+ "loss": 0.8889,
900
+ "step": 620
901
+ },
902
+ {
903
+ "epoch": 2.64,
904
+ "grad_norm": 0.6047803478738842,
905
+ "learning_rate": 8.806135497025181e-07,
906
+ "loss": 0.8712,
907
+ "step": 625
908
+ },
909
+ {
910
+ "epoch": 2.66,
911
+ "grad_norm": 0.6161378090035984,
912
+ "learning_rate": 7.825119989112173e-07,
913
+ "loss": 0.8885,
914
+ "step": 630
915
+ },
916
+ {
917
+ "epoch": 2.68,
918
+ "grad_norm": 0.6233431696221546,
919
+ "learning_rate": 6.899801089469205e-07,
920
+ "loss": 0.8852,
921
+ "step": 635
922
+ },
923
+ {
924
+ "epoch": 2.7,
925
+ "grad_norm": 0.6391554220139581,
926
+ "learning_rate": 6.030737921409169e-07,
927
+ "loss": 0.8773,
928
+ "step": 640
929
+ },
930
+ {
931
+ "epoch": 2.72,
932
+ "grad_norm": 0.6245630190412572,
933
+ "learning_rate": 5.218455615757601e-07,
934
+ "loss": 0.8805,
935
+ "step": 645
936
+ },
937
+ {
938
+ "epoch": 2.74,
939
+ "grad_norm": 0.6100529800808214,
940
+ "learning_rate": 4.4634449935427203e-07,
941
+ "loss": 0.8605,
942
+ "step": 650
943
+ },
944
+ {
945
+ "epoch": 2.76,
946
+ "grad_norm": 0.6121972838225812,
947
+ "learning_rate": 3.7661622694171393e-07,
948
+ "loss": 0.9044,
949
+ "step": 655
950
+ },
951
+ {
952
+ "epoch": 2.78,
953
+ "grad_norm": 0.6334525599084514,
954
+ "learning_rate": 3.127028775990515e-07,
955
+ "loss": 0.8752,
956
+ "step": 660
957
+ },
958
+ {
959
+ "epoch": 2.81,
960
+ "grad_norm": 0.6246892070368814,
961
+ "learning_rate": 2.546430709239578e-07,
962
+ "loss": 0.873,
963
+ "step": 665
964
+ },
965
+ {
966
+ "epoch": 2.83,
967
+ "grad_norm": 0.6189951160404621,
968
+ "learning_rate": 2.02471889514948e-07,
969
+ "loss": 0.8616,
970
+ "step": 670
971
+ },
972
+ {
973
+ "epoch": 2.85,
974
+ "grad_norm": 0.612318312224187,
975
+ "learning_rate": 1.562208577727442e-07,
976
+ "loss": 0.8419,
977
+ "step": 675
978
+ },
979
+ {
980
+ "epoch": 2.87,
981
+ "grad_norm": 0.597268698517341,
982
+ "learning_rate": 1.1591792285167603e-07,
983
+ "loss": 0.863,
984
+ "step": 680
985
+ },
986
+ {
987
+ "epoch": 2.89,
988
+ "grad_norm": 0.6176692124122442,
989
+ "learning_rate": 8.158743777263334e-08,
990
+ "loss": 0.8801,
991
+ "step": 685
992
+ },
993
+ {
994
+ "epoch": 2.91,
995
+ "grad_norm": 0.6020045294431875,
996
+ "learning_rate": 5.325014670776951e-08,
997
+ "loss": 0.8632,
998
+ "step": 690
999
+ },
1000
+ {
1001
+ "epoch": 2.93,
1002
+ "grad_norm": 0.6387655106971034,
1003
+ "learning_rate": 3.092317244584919e-08,
1004
+ "loss": 0.9029,
1005
+ "step": 695
1006
+ },
1007
+ {
1008
+ "epoch": 2.95,
1009
+ "grad_norm": 0.6272250942520349,
1010
+ "learning_rate": 1.4620006045816814e-08,
1011
+ "loss": 0.9094,
1012
+ "step": 700
1013
+ },
1014
+ {
1015
+ "epoch": 2.97,
1016
+ "grad_norm": 0.6245247048439003,
1017
+ "learning_rate": 4.3504986848297295e-09,
1018
+ "loss": 0.8741,
1019
+ "step": 705
1020
+ },
1021
+ {
1022
+ "epoch": 3.0,
1023
+ "grad_norm": 0.6085774534918146,
1024
+ "learning_rate": 1.2085570569642102e-10,
1025
+ "loss": 0.8734,
1026
+ "step": 710
1027
+ },
1028
+ {
1029
+ "epoch": 3.0,
1030
+ "eval_loss": 1.0886437892913818,
1031
+ "eval_runtime": 5.0486,
1032
+ "eval_samples_per_second": 291.961,
1033
+ "eval_steps_per_second": 4.754,
1034
+ "step": 711
1035
+ },
1036
+ {
1037
+ "epoch": 3.0,
1038
+ "step": 711,
1039
+ "total_flos": 277125248581632.0,
1040
+ "train_loss": 0.9885472514458347,
1041
+ "train_runtime": 1164.5291,
1042
+ "train_samples_per_second": 77.885,
1043
+ "train_steps_per_second": 0.611
1044
+ }
1045
+ ],
1046
+ "logging_steps": 5,
1047
+ "max_steps": 711,
1048
+ "num_input_tokens_seen": 0,
1049
+ "num_train_epochs": 3,
1050
+ "save_steps": 100,
1051
+ "total_flos": 277125248581632.0,
1052
+ "train_batch_size": 16,
1053
+ "trial_name": null,
1054
+ "trial_params": null
1055
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa6275ea3a7ab0b52842a3362c23f21aec0ad272d596daabddb4e6c8543f247
3
+ size 6520
vocab.json ADDED
The diff for this file is too large to render. See raw diff