Ritvik19 commited on
Commit
f898705
1 Parent(s): 2a0965b

Upload 13 files

Browse files
README.md CHANGED
@@ -1,3 +1,52 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ base_model: h2oai/h2o-danube-1.8b-base
8
+ datasets:
9
+ - HuggingFaceH4/ultrachat_200k
10
+ model-index:
11
+ - name: zephyr-danube-sft-qlora
12
+ results: []
13
+ ---
14
+
15
+ **Note**: This model card has been generated automatically according to the information the Trainer had access to.
16
+ Visit the [model card](https://ritvik19.github.io/zephyr-mini/) to see the full description.
17
+
18
+ # zephyr-danube-sft-qlora
19
+
20
+ This model is a fine-tuned version of [h2oai/h2o-danube-1.8b-base](https://huggingface.co/h2oai/h2o-danube-1.8b-base) on the HuggingFaceH4/ultrachat_200k dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.0893
23
+
24
+ ### Training hyperparameters
25
+
26
+ The following hyperparameters were used during training:
27
+ - learning_rate: 0.0002
28
+ - train_batch_size: 1
29
+ - eval_batch_size: 1
30
+ - seed: 42
31
+ - distributed_type: multi-GPU
32
+ - gradient_accumulation_steps: 128
33
+ - total_train_batch_size: 128
34
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
35
+ - lr_scheduler_type: cosine
36
+ - lr_scheduler_warmup_ratio: 0.1
37
+ - num_epochs: 1
38
+
39
+ ### Training results
40
+
41
+ | Training Loss | Epoch | Step | Validation Loss |
42
+ |:-------------:|:------:|:----:|:---------------:|
43
+ | 1.0883 | 0.9998 | 1140 | 1.0893 |
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - PEFT 0.7.1
49
+ - Transformers 4.40.1
50
+ - Pytorch 2.1.2+cu121
51
+ - Datasets 2.19.0
52
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "h2oai/h2o-danube-1.8b-base",
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": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "down_proj",
23
+ "gate_proj",
24
+ "q_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "o_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8e9a952c22d7321bd74f842dfcf17749e2616e7af1b9f06e11bbf7b007226a
3
+ size 34647816
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997807498355624,
3
+ "eval_loss": 1.089297890663147,
4
+ "eval_runtime": 2019.9951,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 7.996,
7
+ "eval_steps_per_second": 7.996,
8
+ "total_flos": 3.167597749864497e+18,
9
+ "train_loss": 0.80264539467661,
10
+ "train_runtime": 53655.2232,
11
+ "train_samples": 207864,
12
+ "train_samples_per_second": 2.72,
13
+ "train_steps_per_second": 0.021
14
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "h2oai/h2o-danube-1.8b-base",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2560,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 6912,
13
+ "max_position_embeddings": 16384,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "sliding_window": 4096,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997807498355624,
3
+ "eval_loss": 1.089297890663147,
4
+ "eval_runtime": 2019.9951,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 7.996,
7
+ "eval_steps_per_second": 7.996
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "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 %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997807498355624,
3
+ "total_flos": 3.167597749864497e+18,
4
+ "train_loss": 0.80264539467661,
5
+ "train_runtime": 53655.2232,
6
+ "train_samples": 207864,
7
+ "train_samples_per_second": 2.72,
8
+ "train_steps_per_second": 0.021
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1641 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997807498355624,
5
+ "eval_steps": 500,
6
+ "global_step": 1140,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0008770006577504934,
13
+ "grad_norm": 0.1337890625,
14
+ "learning_rate": 1.7543859649122807e-06,
15
+ "loss": 1.3755,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0043850032887524665,
20
+ "grad_norm": 0.11865234375,
21
+ "learning_rate": 8.771929824561403e-06,
22
+ "loss": 1.37,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.008770006577504933,
27
+ "grad_norm": 0.12060546875,
28
+ "learning_rate": 1.7543859649122806e-05,
29
+ "loss": 1.3508,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.0131550098662574,
34
+ "grad_norm": 0.1259765625,
35
+ "learning_rate": 2.6315789473684212e-05,
36
+ "loss": 1.3572,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.017540013155009866,
41
+ "grad_norm": 0.1162109375,
42
+ "learning_rate": 3.508771929824561e-05,
43
+ "loss": 1.3438,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.021925016443762334,
48
+ "grad_norm": 0.10986328125,
49
+ "learning_rate": 4.3859649122807014e-05,
50
+ "loss": 1.3356,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.0263100197325148,
55
+ "grad_norm": 0.09814453125,
56
+ "learning_rate": 5.2631578947368424e-05,
57
+ "loss": 1.3111,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.030695023021267268,
62
+ "grad_norm": 0.095703125,
63
+ "learning_rate": 6.140350877192983e-05,
64
+ "loss": 1.2578,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.03508002631001973,
69
+ "grad_norm": 0.07421875,
70
+ "learning_rate": 7.017543859649122e-05,
71
+ "loss": 1.2393,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.0394650295987722,
76
+ "grad_norm": 0.064453125,
77
+ "learning_rate": 7.894736842105263e-05,
78
+ "loss": 1.2206,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.04385003288752467,
83
+ "grad_norm": 0.049072265625,
84
+ "learning_rate": 8.771929824561403e-05,
85
+ "loss": 1.1976,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.048235036176277134,
90
+ "grad_norm": 0.044921875,
91
+ "learning_rate": 9.649122807017544e-05,
92
+ "loss": 1.1976,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.0526200394650296,
97
+ "grad_norm": 0.042724609375,
98
+ "learning_rate": 0.00010526315789473685,
99
+ "loss": 1.1789,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.05700504275378206,
104
+ "grad_norm": 0.042236328125,
105
+ "learning_rate": 0.00011403508771929824,
106
+ "loss": 1.1716,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.061390046042534535,
111
+ "grad_norm": 0.044677734375,
112
+ "learning_rate": 0.00012280701754385965,
113
+ "loss": 1.1691,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.065775049331287,
118
+ "grad_norm": 0.03857421875,
119
+ "learning_rate": 0.00013157894736842108,
120
+ "loss": 1.1533,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.07016005262003946,
125
+ "grad_norm": 0.041748046875,
126
+ "learning_rate": 0.00014035087719298245,
127
+ "loss": 1.1353,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.07454505590879193,
132
+ "grad_norm": 0.04833984375,
133
+ "learning_rate": 0.00014912280701754387,
134
+ "loss": 1.1404,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.0789300591975444,
139
+ "grad_norm": 0.046142578125,
140
+ "learning_rate": 0.00015789473684210527,
141
+ "loss": 1.1498,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.08331506248629686,
146
+ "grad_norm": 0.04443359375,
147
+ "learning_rate": 0.0001666666666666667,
148
+ "loss": 1.1125,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.08770006577504934,
153
+ "grad_norm": 0.049560546875,
154
+ "learning_rate": 0.00017543859649122806,
155
+ "loss": 1.1447,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.0920850690638018,
160
+ "grad_norm": 0.05712890625,
161
+ "learning_rate": 0.00018421052631578948,
162
+ "loss": 1.1351,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.09647007235255427,
167
+ "grad_norm": 0.04931640625,
168
+ "learning_rate": 0.00019298245614035088,
169
+ "loss": 1.1294,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.10085507564130673,
174
+ "grad_norm": 0.05029296875,
175
+ "learning_rate": 0.00019999953121394002,
176
+ "loss": 1.1315,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.1052400789300592,
181
+ "grad_norm": 0.060546875,
182
+ "learning_rate": 0.00019998312416333227,
183
+ "loss": 1.1284,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.10962508221881166,
188
+ "grad_norm": 0.04931640625,
189
+ "learning_rate": 0.00019994328220474688,
190
+ "loss": 1.136,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.11401008550756413,
195
+ "grad_norm": 0.052001953125,
196
+ "learning_rate": 0.0001998800146766861,
197
+ "loss": 1.1213,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.11839508879631659,
202
+ "grad_norm": 0.064453125,
203
+ "learning_rate": 0.00019979333640833947,
204
+ "loss": 1.1152,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.12278009208506907,
209
+ "grad_norm": 0.051513671875,
210
+ "learning_rate": 0.00019968326771610797,
211
+ "loss": 1.1193,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.12716509537382154,
216
+ "grad_norm": 0.05126953125,
217
+ "learning_rate": 0.0001995498343988421,
218
+ "loss": 1.121,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.131550098662574,
223
+ "grad_norm": 0.055419921875,
224
+ "learning_rate": 0.00019939306773179497,
225
+ "loss": 1.1291,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.13593510195132646,
230
+ "grad_norm": 0.04736328125,
231
+ "learning_rate": 0.0001992130044592916,
232
+ "loss": 1.122,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.14032010524007893,
237
+ "grad_norm": 0.05078125,
238
+ "learning_rate": 0.00019900968678611666,
239
+ "loss": 1.1174,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.1447051085288314,
244
+ "grad_norm": 0.06298828125,
245
+ "learning_rate": 0.00019878316236762196,
246
+ "loss": 1.1205,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.14909011181758386,
251
+ "grad_norm": 0.05615234375,
252
+ "learning_rate": 0.00019853348429855672,
253
+ "loss": 1.1086,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.15347511510633632,
258
+ "grad_norm": 0.053955078125,
259
+ "learning_rate": 0.0001982607111006227,
260
+ "loss": 1.1086,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.1578601183950888,
265
+ "grad_norm": 0.052978515625,
266
+ "learning_rate": 0.0001979649067087574,
267
+ "loss": 1.1202,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.16224512168384125,
272
+ "grad_norm": 0.0517578125,
273
+ "learning_rate": 0.00019764614045614836,
274
+ "loss": 1.1248,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.16663012497259372,
279
+ "grad_norm": 0.05615234375,
280
+ "learning_rate": 0.00019730448705798239,
281
+ "loss": 1.1231,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.17101512826134618,
286
+ "grad_norm": 0.05810546875,
287
+ "learning_rate": 0.00019694002659393305,
288
+ "loss": 1.102,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.17540013155009868,
293
+ "grad_norm": 0.056396484375,
294
+ "learning_rate": 0.00019655284448939094,
295
+ "loss": 1.1203,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.17978513483885114,
300
+ "grad_norm": 0.054931640625,
301
+ "learning_rate": 0.00019614303149544102,
302
+ "loss": 1.1073,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.1841701381276036,
307
+ "grad_norm": 0.05029296875,
308
+ "learning_rate": 0.00019571068366759143,
309
+ "loss": 1.1082,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.18855514141635607,
314
+ "grad_norm": 0.054443359375,
315
+ "learning_rate": 0.00019525590234325933,
316
+ "loss": 1.1114,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.19294014470510853,
321
+ "grad_norm": 0.0576171875,
322
+ "learning_rate": 0.00019477879411801844,
323
+ "loss": 1.1007,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.197325147993861,
328
+ "grad_norm": 0.051513671875,
329
+ "learning_rate": 0.00019427947082061432,
330
+ "loss": 1.0978,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.20171015128261346,
335
+ "grad_norm": 0.05419921875,
336
+ "learning_rate": 0.00019375804948675306,
337
+ "loss": 1.0876,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.20609515457136593,
342
+ "grad_norm": 0.050537109375,
343
+ "learning_rate": 0.00019321465233166924,
344
+ "loss": 1.1182,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.2104801578601184,
349
+ "grad_norm": 0.05224609375,
350
+ "learning_rate": 0.00019264940672148018,
351
+ "loss": 1.0853,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.21486516114887086,
356
+ "grad_norm": 0.05224609375,
357
+ "learning_rate": 0.00019206244514333282,
358
+ "loss": 1.1151,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.21925016443762332,
363
+ "grad_norm": 0.050537109375,
364
+ "learning_rate": 0.00019145390517435012,
365
+ "loss": 1.111,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.2236351677263758,
370
+ "grad_norm": 0.048828125,
371
+ "learning_rate": 0.00019082392944938466,
372
+ "loss": 1.1262,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.22802017101512825,
377
+ "grad_norm": 0.046875,
378
+ "learning_rate": 0.00019017266562758659,
379
+ "loss": 1.1036,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.23240517430388072,
384
+ "grad_norm": 0.048095703125,
385
+ "learning_rate": 0.00018950026635779397,
386
+ "loss": 1.1162,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.23679017759263318,
391
+ "grad_norm": 0.049560546875,
392
+ "learning_rate": 0.00018880688924275378,
393
+ "loss": 1.102,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.24117518088138565,
398
+ "grad_norm": 0.05419921875,
399
+ "learning_rate": 0.00018809269680218136,
400
+ "loss": 1.1,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.24556018417013814,
405
+ "grad_norm": 0.050537109375,
406
+ "learning_rate": 0.00018735785643466784,
407
+ "loss": 1.1037,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.2499451874588906,
412
+ "grad_norm": 0.04931640625,
413
+ "learning_rate": 0.00018660254037844388,
414
+ "loss": 1.0826,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.25433019074764307,
419
+ "grad_norm": 0.053466796875,
420
+ "learning_rate": 0.00018582692567100867,
421
+ "loss": 1.1046,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.25871519403639553,
426
+ "grad_norm": 0.05859375,
427
+ "learning_rate": 0.0001850311941076346,
428
+ "loss": 1.082,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.263100197325148,
433
+ "grad_norm": 0.053955078125,
434
+ "learning_rate": 0.00018421553219875658,
435
+ "loss": 1.0945,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.26748520061390046,
440
+ "grad_norm": 0.053955078125,
441
+ "learning_rate": 0.00018338013112625587,
442
+ "loss": 1.0985,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.27187020390265293,
447
+ "grad_norm": 0.051513671875,
448
+ "learning_rate": 0.00018252518669864936,
449
+ "loss": 1.1186,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.2762552071914054,
454
+ "grad_norm": 0.0625,
455
+ "learning_rate": 0.0001816508993051943,
456
+ "loss": 1.1253,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.28064021048015786,
461
+ "grad_norm": 0.05224609375,
462
+ "learning_rate": 0.0001807574738689193,
463
+ "loss": 1.0904,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.2850252137689103,
468
+ "grad_norm": 0.0498046875,
469
+ "learning_rate": 0.00017984511979859263,
470
+ "loss": 1.109,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.2894102170576628,
475
+ "grad_norm": 0.051513671875,
476
+ "learning_rate": 0.00017891405093963938,
477
+ "loss": 1.1041,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.29379522034641525,
482
+ "grad_norm": 0.052734375,
483
+ "learning_rate": 0.00017796448552401825,
484
+ "loss": 1.0927,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.2981802236351677,
489
+ "grad_norm": 0.04931640625,
490
+ "learning_rate": 0.00017699664611907072,
491
+ "loss": 1.1041,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.3025652269239202,
496
+ "grad_norm": 0.0537109375,
497
+ "learning_rate": 0.00017601075957535364,
498
+ "loss": 1.1115,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.30695023021267265,
503
+ "grad_norm": 0.047119140625,
504
+ "learning_rate": 0.0001750070569734681,
505
+ "loss": 1.1088,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.3113352335014251,
510
+ "grad_norm": 0.048583984375,
511
+ "learning_rate": 0.00017398577356989665,
512
+ "loss": 1.0905,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.3157202367901776,
517
+ "grad_norm": 0.04638671875,
518
+ "learning_rate": 0.0001729471487418621,
519
+ "loss": 1.1071,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.32010524007893004,
524
+ "grad_norm": 0.052734375,
525
+ "learning_rate": 0.00017189142593121993,
526
+ "loss": 1.0872,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.3244902433676825,
531
+ "grad_norm": 0.0478515625,
532
+ "learning_rate": 0.00017081885258739846,
533
+ "loss": 1.1054,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.32887524665643497,
538
+ "grad_norm": 0.049072265625,
539
+ "learning_rate": 0.00016972968010939954,
540
+ "loss": 1.1035,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.33326024994518744,
545
+ "grad_norm": 0.05126953125,
546
+ "learning_rate": 0.0001686241637868734,
547
+ "loss": 1.0976,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.3376452532339399,
552
+ "grad_norm": 0.05126953125,
553
+ "learning_rate": 0.00016750256274028152,
554
+ "loss": 1.099,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.34203025652269237,
559
+ "grad_norm": 0.050048828125,
560
+ "learning_rate": 0.00016636513986016213,
561
+ "loss": 1.1267,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.34641525981144483,
566
+ "grad_norm": 0.05224609375,
567
+ "learning_rate": 0.0001652121617455113,
568
+ "loss": 1.101,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.35080026310019735,
573
+ "grad_norm": 0.050048828125,
574
+ "learning_rate": 0.00016404389864129533,
575
+ "loss": 1.1005,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.3551852663889498,
580
+ "grad_norm": 0.049072265625,
581
+ "learning_rate": 0.0001628606243751082,
582
+ "loss": 1.0973,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.3595702696777023,
587
+ "grad_norm": 0.04931640625,
588
+ "learning_rate": 0.00016166261629298995,
589
+ "loss": 1.1016,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.36395527296645475,
594
+ "grad_norm": 0.05517578125,
595
+ "learning_rate": 0.0001604501551944193,
596
+ "loss": 1.0863,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.3683402762552072,
601
+ "grad_norm": 0.05517578125,
602
+ "learning_rate": 0.00015922352526649803,
603
+ "loss": 1.1008,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.3727252795439597,
608
+ "grad_norm": 0.05517578125,
609
+ "learning_rate": 0.0001579830140173403,
610
+ "loss": 1.0999,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.37711028283271214,
615
+ "grad_norm": 0.049072265625,
616
+ "learning_rate": 0.00015672891220868432,
617
+ "loss": 1.0944,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.3814952861214646,
622
+ "grad_norm": 0.048095703125,
623
+ "learning_rate": 0.00015546151378774086,
624
+ "loss": 1.084,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.38588028941021707,
629
+ "grad_norm": 0.049560546875,
630
+ "learning_rate": 0.00015418111581829574,
631
+ "loss": 1.0957,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.39026529269896953,
636
+ "grad_norm": 0.047607421875,
637
+ "learning_rate": 0.00015288801841108093,
638
+ "loss": 1.0823,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.394650295987722,
643
+ "grad_norm": 0.051025390625,
644
+ "learning_rate": 0.00015158252465343242,
645
+ "loss": 1.0925,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.39903529927647446,
650
+ "grad_norm": 0.05029296875,
651
+ "learning_rate": 0.00015026494053824982,
652
+ "loss": 1.0917,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.40342030256522693,
657
+ "grad_norm": 0.05029296875,
658
+ "learning_rate": 0.00014893557489227517,
659
+ "loss": 1.0935,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.4078053058539794,
664
+ "grad_norm": 0.048095703125,
665
+ "learning_rate": 0.00014759473930370736,
666
+ "loss": 1.0795,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.41219030914273186,
671
+ "grad_norm": 0.051025390625,
672
+ "learning_rate": 0.00014624274804916958,
673
+ "loss": 1.0943,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.4165753124314843,
678
+ "grad_norm": 0.05322265625,
679
+ "learning_rate": 0.00014487991802004623,
680
+ "loss": 1.1022,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.4209603157202368,
685
+ "grad_norm": 0.055419921875,
686
+ "learning_rate": 0.00014350656864820733,
687
+ "loss": 1.0849,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.42534531900898925,
692
+ "grad_norm": 0.05224609375,
693
+ "learning_rate": 0.00014212302183113732,
694
+ "loss": 1.0865,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.4297303222977417,
699
+ "grad_norm": 0.05224609375,
700
+ "learning_rate": 0.00014072960185648577,
701
+ "loss": 1.106,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.4341153255864942,
706
+ "grad_norm": 0.04736328125,
707
+ "learning_rate": 0.0001393266353260583,
708
+ "loss": 1.0926,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.43850032887524665,
713
+ "grad_norm": 0.048583984375,
714
+ "learning_rate": 0.00013791445107926478,
715
+ "loss": 1.1091,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.4428853321639991,
720
+ "grad_norm": 0.0478515625,
721
+ "learning_rate": 0.0001364933801160428,
722
+ "loss": 1.0858,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.4472703354527516,
727
+ "grad_norm": 0.048583984375,
728
+ "learning_rate": 0.00013506375551927547,
729
+ "loss": 1.0901,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.45165533874150404,
734
+ "grad_norm": 0.0478515625,
735
+ "learning_rate": 0.0001336259123767203,
736
+ "loss": 1.0852,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.4560403420302565,
741
+ "grad_norm": 0.050048828125,
742
+ "learning_rate": 0.00013218018770246858,
743
+ "loss": 1.0838,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.46042534531900897,
748
+ "grad_norm": 0.052490234375,
749
+ "learning_rate": 0.00013072692035795305,
750
+ "loss": 1.0795,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.46481034860776144,
755
+ "grad_norm": 0.048828125,
756
+ "learning_rate": 0.0001292664509725226,
757
+ "loss": 1.1038,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.4691953518965139,
762
+ "grad_norm": 0.051513671875,
763
+ "learning_rate": 0.00012779912186360268,
764
+ "loss": 1.0937,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.47358035518526637,
769
+ "grad_norm": 0.05126953125,
770
+ "learning_rate": 0.00012632527695645993,
771
+ "loss": 1.08,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.47796535847401883,
776
+ "grad_norm": 0.0498046875,
777
+ "learning_rate": 0.00012484526170359012,
778
+ "loss": 1.0642,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.4823503617627713,
783
+ "grad_norm": 0.051513671875,
784
+ "learning_rate": 0.00012335942300374788,
785
+ "loss": 1.089,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.4867353650515238,
790
+ "grad_norm": 0.05126953125,
791
+ "learning_rate": 0.0001218681091206376,
792
+ "loss": 1.0893,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.4911203683402763,
797
+ "grad_norm": 0.049560546875,
798
+ "learning_rate": 0.00012037166960128443,
799
+ "loss": 1.0996,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.49550537162902875,
804
+ "grad_norm": 0.04736328125,
805
+ "learning_rate": 0.00011887045519410442,
806
+ "loss": 1.0955,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.4998903749177812,
811
+ "grad_norm": 0.050537109375,
812
+ "learning_rate": 0.00011736481776669306,
813
+ "loss": 1.0904,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.5042753782065337,
818
+ "grad_norm": 0.04833984375,
819
+ "learning_rate": 0.00011585511022335142,
820
+ "loss": 1.1074,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.5086603814952861,
825
+ "grad_norm": 0.0498046875,
826
+ "learning_rate": 0.00011434168642236964,
827
+ "loss": 1.0855,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.5130453847840386,
832
+ "grad_norm": 0.052734375,
833
+ "learning_rate": 0.00011282490109308633,
834
+ "loss": 1.0872,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.5174303880727911,
839
+ "grad_norm": 0.050048828125,
840
+ "learning_rate": 0.00011130510975274409,
841
+ "loss": 1.0824,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.5218153913615435,
846
+ "grad_norm": 0.049072265625,
847
+ "learning_rate": 0.0001097826686231604,
848
+ "loss": 1.1002,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.526200394650296,
853
+ "grad_norm": 0.050048828125,
854
+ "learning_rate": 0.00010825793454723325,
855
+ "loss": 1.083,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.5305853979390485,
860
+ "grad_norm": 0.05126953125,
861
+ "learning_rate": 0.00010673126490530112,
862
+ "loss": 1.1003,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.5349704012278009,
867
+ "grad_norm": 0.049072265625,
868
+ "learning_rate": 0.00010520301753137724,
869
+ "loss": 1.0852,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.5393554045165534,
874
+ "grad_norm": 0.050048828125,
875
+ "learning_rate": 0.00010367355062927726,
876
+ "loss": 1.0904,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.5437404078053059,
881
+ "grad_norm": 0.050048828125,
882
+ "learning_rate": 0.00010214322268866032,
883
+ "loss": 1.0839,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.5481254110940583,
888
+ "grad_norm": 0.053466796875,
889
+ "learning_rate": 0.00010061239240100327,
890
+ "loss": 1.079,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.5525104143828108,
895
+ "grad_norm": 0.048583984375,
896
+ "learning_rate": 9.908141857552737e-05,
897
+ "loss": 1.0987,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.5568954176715633,
902
+ "grad_norm": 0.04833984375,
903
+ "learning_rate": 9.755066005509753e-05,
904
+ "loss": 1.075,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.5612804209603157,
909
+ "grad_norm": 0.04931640625,
910
+ "learning_rate": 9.602047563211359e-05,
911
+ "loss": 1.0803,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.5656654242490682,
916
+ "grad_norm": 0.053466796875,
917
+ "learning_rate": 9.449122396441345e-05,
918
+ "loss": 1.1114,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.5700504275378206,
923
+ "grad_norm": 0.048828125,
924
+ "learning_rate": 9.296326349120785e-05,
925
+ "loss": 1.0771,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.5744354308265731,
930
+ "grad_norm": 0.049560546875,
931
+ "learning_rate": 9.143695234906611e-05,
932
+ "loss": 1.0917,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.5788204341153256,
937
+ "grad_norm": 0.049072265625,
938
+ "learning_rate": 8.991264828797319e-05,
939
+ "loss": 1.0843,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.583205437404078,
944
+ "grad_norm": 0.0498046875,
945
+ "learning_rate": 8.839070858747697e-05,
946
+ "loss": 1.0863,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.5875904406928305,
951
+ "grad_norm": 0.0517578125,
952
+ "learning_rate": 8.687148997294621e-05,
953
+ "loss": 1.086,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.591975443981583,
958
+ "grad_norm": 0.05029296875,
959
+ "learning_rate": 8.535534853195786e-05,
960
+ "loss": 1.08,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.5963604472703354,
965
+ "grad_norm": 0.05126953125,
966
+ "learning_rate": 8.384263963083453e-05,
967
+ "loss": 1.0686,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.6007454505590879,
972
+ "grad_norm": 0.051025390625,
973
+ "learning_rate": 8.23337178313504e-05,
974
+ "loss": 1.075,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.6051304538478404,
979
+ "grad_norm": 0.052490234375,
980
+ "learning_rate": 8.082893680762619e-05,
981
+ "loss": 1.0926,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.6095154571365928,
986
+ "grad_norm": 0.051025390625,
987
+ "learning_rate": 7.932864926323161e-05,
988
+ "loss": 1.079,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.6139004604253453,
993
+ "grad_norm": 0.049072265625,
994
+ "learning_rate": 7.783320684851614e-05,
995
+ "loss": 1.0844,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.6182854637140978,
1000
+ "grad_norm": 0.04833984375,
1001
+ "learning_rate": 7.634296007818576e-05,
1002
+ "loss": 1.1056,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.6226704670028502,
1007
+ "grad_norm": 0.049560546875,
1008
+ "learning_rate": 7.485825824914659e-05,
1009
+ "loss": 1.0851,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.6270554702916027,
1014
+ "grad_norm": 0.048828125,
1015
+ "learning_rate": 7.337944935863333e-05,
1016
+ "loss": 1.0786,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.6314404735803552,
1021
+ "grad_norm": 0.050048828125,
1022
+ "learning_rate": 7.190688002264308e-05,
1023
+ "loss": 1.089,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.6358254768691076,
1028
+ "grad_norm": 0.05126953125,
1029
+ "learning_rate": 7.044089539469212e-05,
1030
+ "loss": 1.0826,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.6402104801578601,
1035
+ "grad_norm": 0.0517578125,
1036
+ "learning_rate": 6.898183908491617e-05,
1037
+ "loss": 1.1004,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.6445954834466125,
1042
+ "grad_norm": 0.050537109375,
1043
+ "learning_rate": 6.753005307953167e-05,
1044
+ "loss": 1.0722,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.648980486735365,
1049
+ "grad_norm": 0.050048828125,
1050
+ "learning_rate": 6.608587766067852e-05,
1051
+ "loss": 1.0859,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.6533654900241175,
1056
+ "grad_norm": 0.050048828125,
1057
+ "learning_rate": 6.464965132666163e-05,
1058
+ "loss": 1.1088,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.6577504933128699,
1063
+ "grad_norm": 0.049560546875,
1064
+ "learning_rate": 6.322171071261071e-05,
1065
+ "loss": 1.0726,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.6621354966016224,
1070
+ "grad_norm": 0.049560546875,
1071
+ "learning_rate": 6.180239051157681e-05,
1072
+ "loss": 1.0897,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.6665204998903749,
1077
+ "grad_norm": 0.0478515625,
1078
+ "learning_rate": 6.039202339608432e-05,
1079
+ "loss": 1.0972,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.6709055031791273,
1084
+ "grad_norm": 0.049560546875,
1085
+ "learning_rate": 5.8990939940156e-05,
1086
+ "loss": 1.0884,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.6752905064678798,
1091
+ "grad_norm": 0.04833984375,
1092
+ "learning_rate": 5.7599468541830356e-05,
1093
+ "loss": 1.086,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.6796755097566323,
1098
+ "grad_norm": 0.0478515625,
1099
+ "learning_rate": 5.62179353461888e-05,
1100
+ "loss": 1.0921,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.6840605130453847,
1105
+ "grad_norm": 0.051025390625,
1106
+ "learning_rate": 5.484666416891109e-05,
1107
+ "loss": 1.0834,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.6884455163341372,
1112
+ "grad_norm": 0.04833984375,
1113
+ "learning_rate": 5.3485976420376336e-05,
1114
+ "loss": 1.0827,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.6928305196228897,
1119
+ "grad_norm": 0.050048828125,
1120
+ "learning_rate": 5.2136191030328455e-05,
1121
+ "loss": 1.0851,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.6972155229116422,
1126
+ "grad_norm": 0.0517578125,
1127
+ "learning_rate": 5.079762437312219e-05,
1128
+ "loss": 1.0834,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.7016005262003947,
1133
+ "grad_norm": 0.048583984375,
1134
+ "learning_rate": 4.9470590193569044e-05,
1135
+ "loss": 1.1016,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.7059855294891472,
1140
+ "grad_norm": 0.049560546875,
1141
+ "learning_rate": 4.815539953339865e-05,
1142
+ "loss": 1.0686,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.7103705327778996,
1147
+ "grad_norm": 0.047607421875,
1148
+ "learning_rate": 4.685236065835443e-05,
1149
+ "loss": 1.086,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.7147555360666521,
1154
+ "grad_norm": 0.0498046875,
1155
+ "learning_rate": 4.5561778985939366e-05,
1156
+ "loss": 1.0817,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.7191405393554046,
1161
+ "grad_norm": 0.048583984375,
1162
+ "learning_rate": 4.4283957013829846e-05,
1163
+ "loss": 1.0837,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.723525542644157,
1168
+ "grad_norm": 0.0478515625,
1169
+ "learning_rate": 4.301919424897338e-05,
1170
+ "loss": 1.0791,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.7279105459329095,
1175
+ "grad_norm": 0.0478515625,
1176
+ "learning_rate": 4.176778713738787e-05,
1177
+ "loss": 1.0865,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.732295549221662,
1182
+ "grad_norm": 0.048583984375,
1183
+ "learning_rate": 4.053002899467774e-05,
1184
+ "loss": 1.0842,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.7366805525104144,
1189
+ "grad_norm": 0.050048828125,
1190
+ "learning_rate": 3.9306209937284346e-05,
1191
+ "loss": 1.0939,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.7410655557991669,
1196
+ "grad_norm": 0.048095703125,
1197
+ "learning_rate": 3.809661681448576e-05,
1198
+ "loss": 1.0941,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.7454505590879194,
1203
+ "grad_norm": 0.048583984375,
1204
+ "learning_rate": 3.69015331411628e-05,
1205
+ "loss": 1.0664,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.7498355623766718,
1210
+ "grad_norm": 0.05029296875,
1211
+ "learning_rate": 3.5721239031346066e-05,
1212
+ "loss": 1.0844,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.7542205656654243,
1217
+ "grad_norm": 0.047607421875,
1218
+ "learning_rate": 3.455601113256073e-05,
1219
+ "loss": 1.1036,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.7586055689541767,
1224
+ "grad_norm": 0.048828125,
1225
+ "learning_rate": 3.340612256098316e-05,
1226
+ "loss": 1.0641,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.7629905722429292,
1231
+ "grad_norm": 0.04833984375,
1232
+ "learning_rate": 3.227184283742591e-05,
1233
+ "loss": 1.087,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.7673755755316817,
1238
+ "grad_norm": 0.04833984375,
1239
+ "learning_rate": 3.115343782416483e-05,
1240
+ "loss": 1.0992,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.7717605788204341,
1245
+ "grad_norm": 0.047607421875,
1246
+ "learning_rate": 3.0051169662624225e-05,
1247
+ "loss": 1.0838,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.7761455821091866,
1252
+ "grad_norm": 0.048583984375,
1253
+ "learning_rate": 2.89652967119336e-05,
1254
+ "loss": 1.0899,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.7805305853979391,
1259
+ "grad_norm": 0.048583984375,
1260
+ "learning_rate": 2.789607348837153e-05,
1261
+ "loss": 1.0906,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.7849155886866915,
1266
+ "grad_norm": 0.04736328125,
1267
+ "learning_rate": 2.684375060570965e-05,
1268
+ "loss": 1.0897,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.789300591975444,
1273
+ "grad_norm": 0.04736328125,
1274
+ "learning_rate": 2.5808574716471856e-05,
1275
+ "loss": 1.0857,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.7936855952641965,
1280
+ "grad_norm": 0.050537109375,
1281
+ "learning_rate": 2.4790788454121584e-05,
1282
+ "loss": 1.0973,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.7980705985529489,
1287
+ "grad_norm": 0.04833984375,
1288
+ "learning_rate": 2.379063037619146e-05,
1289
+ "loss": 1.0714,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.8024556018417014,
1294
+ "grad_norm": 0.048095703125,
1295
+ "learning_rate": 2.2808334908367914e-05,
1296
+ "loss": 1.0919,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.8068406051304539,
1301
+ "grad_norm": 0.0478515625,
1302
+ "learning_rate": 2.184413228954468e-05,
1303
+ "loss": 1.082,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.8112256084192063,
1308
+ "grad_norm": 0.0478515625,
1309
+ "learning_rate": 2.0898248517857256e-05,
1310
+ "loss": 1.091,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.8156106117079588,
1315
+ "grad_norm": 0.04833984375,
1316
+ "learning_rate": 1.9970905297711606e-05,
1317
+ "loss": 1.0919,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.8199956149967113,
1322
+ "grad_norm": 0.050048828125,
1323
+ "learning_rate": 1.9062319987819067e-05,
1324
+ "loss": 1.0668,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.8243806182854637,
1329
+ "grad_norm": 0.04833984375,
1330
+ "learning_rate": 1.8172705550250092e-05,
1331
+ "loss": 1.0912,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.8287656215742162,
1336
+ "grad_norm": 0.046630859375,
1337
+ "learning_rate": 1.7302270500518182e-05,
1338
+ "loss": 1.0886,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.8331506248629686,
1343
+ "grad_norm": 0.047607421875,
1344
+ "learning_rate": 1.6451218858706374e-05,
1345
+ "loss": 1.0815,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 0.8375356281517211,
1350
+ "grad_norm": 0.0498046875,
1351
+ "learning_rate": 1.5619750101647114e-05,
1352
+ "loss": 1.1055,
1353
+ "step": 955
1354
+ },
1355
+ {
1356
+ "epoch": 0.8419206314404736,
1357
+ "grad_norm": 0.04833984375,
1358
+ "learning_rate": 1.4808059116167305e-05,
1359
+ "loss": 1.0854,
1360
+ "step": 960
1361
+ },
1362
+ {
1363
+ "epoch": 0.846305634729226,
1364
+ "grad_norm": 0.048828125,
1365
+ "learning_rate": 1.4016336153408893e-05,
1366
+ "loss": 1.1044,
1367
+ "step": 965
1368
+ },
1369
+ {
1370
+ "epoch": 0.8506906380179785,
1371
+ "grad_norm": 0.047607421875,
1372
+ "learning_rate": 1.3244766784236307e-05,
1373
+ "loss": 1.103,
1374
+ "step": 970
1375
+ },
1376
+ {
1377
+ "epoch": 0.855075641306731,
1378
+ "grad_norm": 0.048583984375,
1379
+ "learning_rate": 1.2493531855740625e-05,
1380
+ "loss": 1.0638,
1381
+ "step": 975
1382
+ },
1383
+ {
1384
+ "epoch": 0.8594606445954834,
1385
+ "grad_norm": 0.047119140625,
1386
+ "learning_rate": 1.176280744885121e-05,
1387
+ "loss": 1.067,
1388
+ "step": 980
1389
+ },
1390
+ {
1391
+ "epoch": 0.8638456478842359,
1392
+ "grad_norm": 0.0478515625,
1393
+ "learning_rate": 1.1052764837064178e-05,
1394
+ "loss": 1.0787,
1395
+ "step": 985
1396
+ },
1397
+ {
1398
+ "epoch": 0.8682306511729884,
1399
+ "grad_norm": 0.04833984375,
1400
+ "learning_rate": 1.0363570446297999e-05,
1401
+ "loss": 1.0825,
1402
+ "step": 990
1403
+ },
1404
+ {
1405
+ "epoch": 0.8726156544617408,
1406
+ "grad_norm": 0.047607421875,
1407
+ "learning_rate": 9.695385815885016e-06,
1408
+ "loss": 1.0905,
1409
+ "step": 995
1410
+ },
1411
+ {
1412
+ "epoch": 0.8770006577504933,
1413
+ "grad_norm": 0.048095703125,
1414
+ "learning_rate": 9.048367560708604e-06,
1415
+ "loss": 1.0723,
1416
+ "step": 1000
1417
+ },
1418
+ {
1419
+ "epoch": 0.8813856610392458,
1420
+ "grad_norm": 0.0478515625,
1421
+ "learning_rate": 8.422667334494249e-06,
1422
+ "loss": 1.1059,
1423
+ "step": 1005
1424
+ },
1425
+ {
1426
+ "epoch": 0.8857706643279982,
1427
+ "grad_norm": 0.047607421875,
1428
+ "learning_rate": 7.818431794263836e-06,
1429
+ "loss": 1.1027,
1430
+ "step": 1010
1431
+ },
1432
+ {
1433
+ "epoch": 0.8901556676167507,
1434
+ "grad_norm": 0.048095703125,
1435
+ "learning_rate": 7.235802565960714e-06,
1436
+ "loss": 1.0733,
1437
+ "step": 1015
1438
+ },
1439
+ {
1440
+ "epoch": 0.8945406709055032,
1441
+ "grad_norm": 0.051025390625,
1442
+ "learning_rate": 6.674916211254289e-06,
1443
+ "loss": 1.0807,
1444
+ "step": 1020
1445
+ },
1446
+ {
1447
+ "epoch": 0.8989256741942556,
1448
+ "grad_norm": 0.05810546875,
1449
+ "learning_rate": 6.1359041955315725e-06,
1450
+ "loss": 1.0729,
1451
+ "step": 1025
1452
+ },
1453
+ {
1454
+ "epoch": 0.9033106774830081,
1455
+ "grad_norm": 0.0478515625,
1456
+ "learning_rate": 5.618892857083069e-06,
1457
+ "loss": 1.0816,
1458
+ "step": 1030
1459
+ },
1460
+ {
1461
+ "epoch": 0.9076956807717605,
1462
+ "grad_norm": 0.047607421875,
1463
+ "learning_rate": 5.124003377490582e-06,
1464
+ "loss": 1.0853,
1465
+ "step": 1035
1466
+ },
1467
+ {
1468
+ "epoch": 0.912080684060513,
1469
+ "grad_norm": 0.049560546875,
1470
+ "learning_rate": 4.65135175322361e-06,
1471
+ "loss": 1.0829,
1472
+ "step": 1040
1473
+ },
1474
+ {
1475
+ "epoch": 0.9164656873492655,
1476
+ "grad_norm": 0.047607421875,
1477
+ "learning_rate": 4.20104876845111e-06,
1478
+ "loss": 1.0797,
1479
+ "step": 1045
1480
+ },
1481
+ {
1482
+ "epoch": 0.9208506906380179,
1483
+ "grad_norm": 0.0478515625,
1484
+ "learning_rate": 3.7731999690749585e-06,
1485
+ "loss": 1.0908,
1486
+ "step": 1050
1487
+ },
1488
+ {
1489
+ "epoch": 0.9252356939267704,
1490
+ "grad_norm": 0.04736328125,
1491
+ "learning_rate": 3.367905637991142e-06,
1492
+ "loss": 1.0784,
1493
+ "step": 1055
1494
+ },
1495
+ {
1496
+ "epoch": 0.9296206972155229,
1497
+ "grad_norm": 0.0478515625,
1498
+ "learning_rate": 2.9852607715846193e-06,
1499
+ "loss": 1.101,
1500
+ "step": 1060
1501
+ },
1502
+ {
1503
+ "epoch": 0.9340057005042753,
1504
+ "grad_norm": 0.048095703125,
1505
+ "learning_rate": 2.6253550574632303e-06,
1506
+ "loss": 1.1063,
1507
+ "step": 1065
1508
+ },
1509
+ {
1510
+ "epoch": 0.9383907037930278,
1511
+ "grad_norm": 0.0478515625,
1512
+ "learning_rate": 2.288272853436013e-06,
1513
+ "loss": 1.0768,
1514
+ "step": 1070
1515
+ },
1516
+ {
1517
+ "epoch": 0.9427757070817803,
1518
+ "grad_norm": 0.049072265625,
1519
+ "learning_rate": 1.974093167740565e-06,
1520
+ "loss": 1.0755,
1521
+ "step": 1075
1522
+ },
1523
+ {
1524
+ "epoch": 0.9471607103705327,
1525
+ "grad_norm": 0.04833984375,
1526
+ "learning_rate": 1.6828896405244988e-06,
1527
+ "loss": 1.0714,
1528
+ "step": 1080
1529
+ },
1530
+ {
1531
+ "epoch": 0.9515457136592852,
1532
+ "grad_norm": 0.047119140625,
1533
+ "learning_rate": 1.4147305265850175e-06,
1534
+ "loss": 1.085,
1535
+ "step": 1085
1536
+ },
1537
+ {
1538
+ "epoch": 0.9559307169480377,
1539
+ "grad_norm": 0.047119140625,
1540
+ "learning_rate": 1.1696786793707781e-06,
1541
+ "loss": 1.0816,
1542
+ "step": 1090
1543
+ },
1544
+ {
1545
+ "epoch": 0.9603157202367901,
1546
+ "grad_norm": 0.046875,
1547
+ "learning_rate": 9.477915362496758e-07,
1548
+ "loss": 1.0925,
1549
+ "step": 1095
1550
+ },
1551
+ {
1552
+ "epoch": 0.9647007235255426,
1553
+ "grad_norm": 0.0478515625,
1554
+ "learning_rate": 7.491211050462798e-07,
1555
+ "loss": 1.0662,
1556
+ "step": 1100
1557
+ },
1558
+ {
1559
+ "epoch": 0.9690857268142951,
1560
+ "grad_norm": 0.048095703125,
1561
+ "learning_rate": 5.737139518517509e-07,
1562
+ "loss": 1.0941,
1563
+ "step": 1105
1564
+ },
1565
+ {
1566
+ "epoch": 0.9734707301030476,
1567
+ "grad_norm": 0.0498046875,
1568
+ "learning_rate": 4.216111901092501e-07,
1569
+ "loss": 1.086,
1570
+ "step": 1110
1571
+ },
1572
+ {
1573
+ "epoch": 0.9778557333918001,
1574
+ "grad_norm": 0.0478515625,
1575
+ "learning_rate": 2.9284847097746923e-07,
1576
+ "loss": 1.0768,
1577
+ "step": 1115
1578
+ },
1579
+ {
1580
+ "epoch": 0.9822407366805526,
1581
+ "grad_norm": 0.04736328125,
1582
+ "learning_rate": 1.8745597497433765e-07,
1583
+ "loss": 1.0733,
1584
+ "step": 1120
1585
+ },
1586
+ {
1587
+ "epoch": 0.986625739969305,
1588
+ "grad_norm": 0.04833984375,
1589
+ "learning_rate": 1.0545840490313596e-07,
1590
+ "loss": 1.0981,
1591
+ "step": 1125
1592
+ },
1593
+ {
1594
+ "epoch": 0.9910107432580575,
1595
+ "grad_norm": 0.05029296875,
1596
+ "learning_rate": 4.687498006236135e-08,
1597
+ "loss": 1.1037,
1598
+ "step": 1130
1599
+ },
1600
+ {
1601
+ "epoch": 0.99539574654681,
1602
+ "grad_norm": 0.0478515625,
1603
+ "learning_rate": 1.1719431740997433e-08,
1604
+ "loss": 1.0715,
1605
+ "step": 1135
1606
+ },
1607
+ {
1608
+ "epoch": 0.9997807498355624,
1609
+ "grad_norm": 0.0478515625,
1610
+ "learning_rate": 0.0,
1611
+ "loss": 1.0883,
1612
+ "step": 1140
1613
+ },
1614
+ {
1615
+ "epoch": 0.9997807498355624,
1616
+ "eval_loss": 1.089297890663147,
1617
+ "eval_runtime": 2048.9326,
1618
+ "eval_samples_per_second": 7.883,
1619
+ "eval_steps_per_second": 7.883,
1620
+ "step": 1140
1621
+ },
1622
+ {
1623
+ "epoch": 0.9997807498355624,
1624
+ "step": 1140,
1625
+ "total_flos": 3.167597749864497e+18,
1626
+ "train_loss": 0.80264539467661,
1627
+ "train_runtime": 53655.2232,
1628
+ "train_samples_per_second": 2.72,
1629
+ "train_steps_per_second": 0.021
1630
+ }
1631
+ ],
1632
+ "logging_steps": 5,
1633
+ "max_steps": 1140,
1634
+ "num_input_tokens_seen": 0,
1635
+ "num_train_epochs": 1,
1636
+ "save_steps": 100,
1637
+ "total_flos": 3.167597749864497e+18,
1638
+ "train_batch_size": 1,
1639
+ "trial_name": null,
1640
+ "trial_params": null
1641
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f97d97dd851eba30db4d442104f8929ef92832e214a10988afea71c04c934f3
3
+ size 5112