Upload checkpoint Qwen2.5-Coder-CONTROL-checkpoints_python_only_2k-1.5B-Base-1 at epoch 1
Browse files- .gitattributes +1 -0
- added_tokens.json +25 -0
- config.json +59 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +216 -0
- trainer_state.json +839 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|PAD_TOKEN|>": 151665,
|
| 5 |
+
"<|box_end|>": 151649,
|
| 6 |
+
"<|box_start|>": 151648,
|
| 7 |
+
"<|endoftext|>": 151643,
|
| 8 |
+
"<|file_sep|>": 151664,
|
| 9 |
+
"<|fim_middle|>": 151660,
|
| 10 |
+
"<|fim_pad|>": 151662,
|
| 11 |
+
"<|fim_prefix|>": 151659,
|
| 12 |
+
"<|fim_suffix|>": 151661,
|
| 13 |
+
"<|im_end|>": 151645,
|
| 14 |
+
"<|im_start|>": 151644,
|
| 15 |
+
"<|image_pad|>": 151655,
|
| 16 |
+
"<|object_ref_end|>": 151647,
|
| 17 |
+
"<|object_ref_start|>": 151646,
|
| 18 |
+
"<|quad_end|>": 151651,
|
| 19 |
+
"<|quad_start|>": 151650,
|
| 20 |
+
"<|repo_name|>": 151663,
|
| 21 |
+
"<|video_pad|>": 151656,
|
| 22 |
+
"<|vision_end|>": 151653,
|
| 23 |
+
"<|vision_pad|>": 151654,
|
| 24 |
+
"<|vision_start|>": 151652
|
| 25 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1536,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 8960,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention"
|
| 41 |
+
],
|
| 42 |
+
"max_position_embeddings": 32768,
|
| 43 |
+
"max_window_layers": 21,
|
| 44 |
+
"model_type": "qwen2",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 28,
|
| 47 |
+
"num_key_value_heads": 2,
|
| 48 |
+
"pad_token_id": 151665,
|
| 49 |
+
"rms_norm_eps": 1e-06,
|
| 50 |
+
"rope_scaling": null,
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
+
"sliding_window": null,
|
| 53 |
+
"tie_word_embeddings": true,
|
| 54 |
+
"transformers_version": "4.57.6",
|
| 55 |
+
"unsloth_fixed": true,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"use_sliding_window": false,
|
| 58 |
+
"vocab_size": 151936
|
| 59 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token_id": [
|
| 3 |
+
151643
|
| 4 |
+
],
|
| 5 |
+
"max_length": 32768,
|
| 6 |
+
"max_new_tokens": 2048,
|
| 7 |
+
"pad_token_id": 151665,
|
| 8 |
+
"transformers_version": "4.57.6"
|
| 9 |
+
}
|
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 sha256:892f3ae8aaa866ea2d29716fd8695046f41b87ef799de4479cda3c4b1abb6157
|
| 3 |
+
size 3087467144
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c86002645fba13f42c9a6adcaf34769986ff318545cc24489871bcbf0945bafa
|
| 3 |
+
size 6175153765
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8ac1c2fe59d2a03376d417d7525db3bd338cc4b368f6b71ff3962a7e105b44d
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|PAD_TOKEN|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
|
| 3 |
+
size 11422086
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,216 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<|PAD_TOKEN|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
}
|
| 189 |
+
},
|
| 190 |
+
"additional_special_tokens": [
|
| 191 |
+
"<|im_start|>",
|
| 192 |
+
"<|im_end|>",
|
| 193 |
+
"<|object_ref_start|>",
|
| 194 |
+
"<|object_ref_end|>",
|
| 195 |
+
"<|box_start|>",
|
| 196 |
+
"<|box_end|>",
|
| 197 |
+
"<|quad_start|>",
|
| 198 |
+
"<|quad_end|>",
|
| 199 |
+
"<|vision_start|>",
|
| 200 |
+
"<|vision_end|>",
|
| 201 |
+
"<|vision_pad|>",
|
| 202 |
+
"<|image_pad|>",
|
| 203 |
+
"<|video_pad|>"
|
| 204 |
+
],
|
| 205 |
+
"bos_token": null,
|
| 206 |
+
"clean_up_tokenization_spaces": false,
|
| 207 |
+
"eos_token": "<|endoftext|>",
|
| 208 |
+
"errors": "replace",
|
| 209 |
+
"extra_special_tokens": {},
|
| 210 |
+
"model_max_length": 2048,
|
| 211 |
+
"pad_token": "<|PAD_TOKEN|>",
|
| 212 |
+
"padding_side": "left",
|
| 213 |
+
"split_special_tokens": false,
|
| 214 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 215 |
+
"unk_token": null
|
| 216 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,839 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 115,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008705114254624592,
|
| 14 |
+
"grad_norm": 1.703125,
|
| 15 |
+
"learning_rate": 5e-05,
|
| 16 |
+
"loss": 0.8632,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.017410228509249184,
|
| 21 |
+
"grad_norm": 2.015625,
|
| 22 |
+
"learning_rate": 4.9956521739130436e-05,
|
| 23 |
+
"loss": 0.7891,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.026115342763873776,
|
| 28 |
+
"grad_norm": 8.375,
|
| 29 |
+
"learning_rate": 4.9913043478260876e-05,
|
| 30 |
+
"loss": 0.7896,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03482045701849837,
|
| 35 |
+
"grad_norm": 3.328125,
|
| 36 |
+
"learning_rate": 4.986956521739131e-05,
|
| 37 |
+
"loss": 0.9271,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04352557127312296,
|
| 42 |
+
"grad_norm": 1.640625,
|
| 43 |
+
"learning_rate": 4.9826086956521736e-05,
|
| 44 |
+
"loss": 0.9154,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05223068552774755,
|
| 49 |
+
"grad_norm": 1.5390625,
|
| 50 |
+
"learning_rate": 4.9782608695652176e-05,
|
| 51 |
+
"loss": 0.9267,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.060935799782372145,
|
| 56 |
+
"grad_norm": 2.71875,
|
| 57 |
+
"learning_rate": 4.973913043478261e-05,
|
| 58 |
+
"loss": 0.8189,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06964091403699674,
|
| 63 |
+
"grad_norm": 1.5859375,
|
| 64 |
+
"learning_rate": 4.969565217391304e-05,
|
| 65 |
+
"loss": 0.8018,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07834602829162132,
|
| 70 |
+
"grad_norm": 1.359375,
|
| 71 |
+
"learning_rate": 4.9652173913043483e-05,
|
| 72 |
+
"loss": 0.9439,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08705114254624592,
|
| 77 |
+
"grad_norm": 2.375,
|
| 78 |
+
"learning_rate": 4.960869565217392e-05,
|
| 79 |
+
"loss": 0.8444,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0957562568008705,
|
| 84 |
+
"grad_norm": 2.125,
|
| 85 |
+
"learning_rate": 4.956521739130435e-05,
|
| 86 |
+
"loss": 1.013,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1044613710554951,
|
| 91 |
+
"grad_norm": 1.7109375,
|
| 92 |
+
"learning_rate": 4.9521739130434784e-05,
|
| 93 |
+
"loss": 1.1719,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11316648531011969,
|
| 98 |
+
"grad_norm": 1.4296875,
|
| 99 |
+
"learning_rate": 4.947826086956522e-05,
|
| 100 |
+
"loss": 1.0034,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.12187159956474429,
|
| 105 |
+
"grad_norm": 1.25,
|
| 106 |
+
"learning_rate": 4.943478260869566e-05,
|
| 107 |
+
"loss": 1.0015,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1305767138193689,
|
| 112 |
+
"grad_norm": 1.25,
|
| 113 |
+
"learning_rate": 4.939130434782609e-05,
|
| 114 |
+
"loss": 0.9413,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.13928182807399347,
|
| 119 |
+
"grad_norm": 1.5546875,
|
| 120 |
+
"learning_rate": 4.9347826086956524e-05,
|
| 121 |
+
"loss": 1.0435,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14798694232861806,
|
| 126 |
+
"grad_norm": 2.265625,
|
| 127 |
+
"learning_rate": 4.930434782608696e-05,
|
| 128 |
+
"loss": 0.9285,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.15669205658324264,
|
| 133 |
+
"grad_norm": 1.3046875,
|
| 134 |
+
"learning_rate": 4.926086956521739e-05,
|
| 135 |
+
"loss": 0.91,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.16539717083786726,
|
| 140 |
+
"grad_norm": 1.296875,
|
| 141 |
+
"learning_rate": 4.9217391304347824e-05,
|
| 142 |
+
"loss": 0.937,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.17410228509249184,
|
| 147 |
+
"grad_norm": 1.28125,
|
| 148 |
+
"learning_rate": 4.9173913043478265e-05,
|
| 149 |
+
"loss": 0.9194,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.18280739934711643,
|
| 154 |
+
"grad_norm": 1.203125,
|
| 155 |
+
"learning_rate": 4.91304347826087e-05,
|
| 156 |
+
"loss": 0.9392,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.191512513601741,
|
| 161 |
+
"grad_norm": 1.3203125,
|
| 162 |
+
"learning_rate": 4.908695652173913e-05,
|
| 163 |
+
"loss": 0.935,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.20021762785636563,
|
| 168 |
+
"grad_norm": 1.2421875,
|
| 169 |
+
"learning_rate": 4.904347826086957e-05,
|
| 170 |
+
"loss": 0.7352,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2089227421109902,
|
| 175 |
+
"grad_norm": 1.2578125,
|
| 176 |
+
"learning_rate": 4.9e-05,
|
| 177 |
+
"loss": 0.8006,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2176278563656148,
|
| 182 |
+
"grad_norm": 1.3046875,
|
| 183 |
+
"learning_rate": 4.895652173913044e-05,
|
| 184 |
+
"loss": 1.1003,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22633297062023938,
|
| 189 |
+
"grad_norm": 1.578125,
|
| 190 |
+
"learning_rate": 4.891304347826087e-05,
|
| 191 |
+
"loss": 0.8786,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.235038084874864,
|
| 196 |
+
"grad_norm": 1.390625,
|
| 197 |
+
"learning_rate": 4.8869565217391305e-05,
|
| 198 |
+
"loss": 0.9133,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.24374319912948858,
|
| 203 |
+
"grad_norm": 1.109375,
|
| 204 |
+
"learning_rate": 4.8826086956521746e-05,
|
| 205 |
+
"loss": 0.9822,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.25244831338411317,
|
| 210 |
+
"grad_norm": 1.6640625,
|
| 211 |
+
"learning_rate": 4.878260869565218e-05,
|
| 212 |
+
"loss": 1.0016,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2611534276387378,
|
| 217 |
+
"grad_norm": 1.34375,
|
| 218 |
+
"learning_rate": 4.873913043478261e-05,
|
| 219 |
+
"loss": 1.1215,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.26985854189336234,
|
| 224 |
+
"grad_norm": 1.171875,
|
| 225 |
+
"learning_rate": 4.8695652173913046e-05,
|
| 226 |
+
"loss": 1.1457,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27856365614798695,
|
| 231 |
+
"grad_norm": 1.3671875,
|
| 232 |
+
"learning_rate": 4.865217391304348e-05,
|
| 233 |
+
"loss": 1.0368,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.28726877040261156,
|
| 238 |
+
"grad_norm": 1.140625,
|
| 239 |
+
"learning_rate": 4.860869565217391e-05,
|
| 240 |
+
"loss": 0.9539,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2959738846572361,
|
| 245 |
+
"grad_norm": 1.4296875,
|
| 246 |
+
"learning_rate": 4.856521739130435e-05,
|
| 247 |
+
"loss": 0.9165,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.30467899891186073,
|
| 252 |
+
"grad_norm": 1.2265625,
|
| 253 |
+
"learning_rate": 4.8521739130434786e-05,
|
| 254 |
+
"loss": 1.03,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3133841131664853,
|
| 259 |
+
"grad_norm": 1.5703125,
|
| 260 |
+
"learning_rate": 4.847826086956522e-05,
|
| 261 |
+
"loss": 1.2848,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3220892274211099,
|
| 266 |
+
"grad_norm": 1.21875,
|
| 267 |
+
"learning_rate": 4.843478260869565e-05,
|
| 268 |
+
"loss": 0.8663,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.3307943416757345,
|
| 273 |
+
"grad_norm": 1.125,
|
| 274 |
+
"learning_rate": 4.839130434782609e-05,
|
| 275 |
+
"loss": 0.9547,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3394994559303591,
|
| 280 |
+
"grad_norm": 1.328125,
|
| 281 |
+
"learning_rate": 4.834782608695652e-05,
|
| 282 |
+
"loss": 0.872,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3482045701849837,
|
| 287 |
+
"grad_norm": 1.140625,
|
| 288 |
+
"learning_rate": 4.830434782608696e-05,
|
| 289 |
+
"loss": 0.8424,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.35690968443960824,
|
| 294 |
+
"grad_norm": 1.2578125,
|
| 295 |
+
"learning_rate": 4.8260869565217394e-05,
|
| 296 |
+
"loss": 0.8246,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.36561479869423286,
|
| 301 |
+
"grad_norm": 1.3046875,
|
| 302 |
+
"learning_rate": 4.8217391304347834e-05,
|
| 303 |
+
"loss": 0.8326,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.37431991294885747,
|
| 308 |
+
"grad_norm": 1.2109375,
|
| 309 |
+
"learning_rate": 4.817391304347826e-05,
|
| 310 |
+
"loss": 0.9043,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.383025027203482,
|
| 315 |
+
"grad_norm": 1.296875,
|
| 316 |
+
"learning_rate": 4.8130434782608694e-05,
|
| 317 |
+
"loss": 0.8888,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.39173014145810664,
|
| 322 |
+
"grad_norm": 1.2265625,
|
| 323 |
+
"learning_rate": 4.8086956521739134e-05,
|
| 324 |
+
"loss": 0.778,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.40043525571273125,
|
| 329 |
+
"grad_norm": 1.0546875,
|
| 330 |
+
"learning_rate": 4.804347826086957e-05,
|
| 331 |
+
"loss": 0.8684,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4091403699673558,
|
| 336 |
+
"grad_norm": 1.5078125,
|
| 337 |
+
"learning_rate": 4.8e-05,
|
| 338 |
+
"loss": 0.9351,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.4178454842219804,
|
| 343 |
+
"grad_norm": 1.2421875,
|
| 344 |
+
"learning_rate": 4.795652173913044e-05,
|
| 345 |
+
"loss": 0.8708,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.426550598476605,
|
| 350 |
+
"grad_norm": 1.28125,
|
| 351 |
+
"learning_rate": 4.7913043478260875e-05,
|
| 352 |
+
"loss": 0.9919,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4352557127312296,
|
| 357 |
+
"grad_norm": 1.1953125,
|
| 358 |
+
"learning_rate": 4.78695652173913e-05,
|
| 359 |
+
"loss": 0.8166,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4439608269858542,
|
| 364 |
+
"grad_norm": 1.3203125,
|
| 365 |
+
"learning_rate": 4.782608695652174e-05,
|
| 366 |
+
"loss": 0.9542,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.45266594124047876,
|
| 371 |
+
"grad_norm": 1.2109375,
|
| 372 |
+
"learning_rate": 4.7782608695652175e-05,
|
| 373 |
+
"loss": 1.0959,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4613710554951034,
|
| 378 |
+
"grad_norm": 1.140625,
|
| 379 |
+
"learning_rate": 4.773913043478261e-05,
|
| 380 |
+
"loss": 0.8695,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.470076169749728,
|
| 385 |
+
"grad_norm": 1.5234375,
|
| 386 |
+
"learning_rate": 4.769565217391305e-05,
|
| 387 |
+
"loss": 1.1411,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.47878128400435255,
|
| 392 |
+
"grad_norm": 1.125,
|
| 393 |
+
"learning_rate": 4.765217391304348e-05,
|
| 394 |
+
"loss": 0.8354,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.48748639825897716,
|
| 399 |
+
"grad_norm": 1.390625,
|
| 400 |
+
"learning_rate": 4.7608695652173916e-05,
|
| 401 |
+
"loss": 0.9133,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4961915125136017,
|
| 406 |
+
"grad_norm": 1.2578125,
|
| 407 |
+
"learning_rate": 4.756521739130435e-05,
|
| 408 |
+
"loss": 0.9042,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5048966267682263,
|
| 413 |
+
"grad_norm": 1.28125,
|
| 414 |
+
"learning_rate": 4.752173913043478e-05,
|
| 415 |
+
"loss": 0.9707,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5136017410228509,
|
| 420 |
+
"grad_norm": 1.2734375,
|
| 421 |
+
"learning_rate": 4.747826086956522e-05,
|
| 422 |
+
"loss": 0.7845,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5223068552774756,
|
| 427 |
+
"grad_norm": 1.3046875,
|
| 428 |
+
"learning_rate": 4.7434782608695656e-05,
|
| 429 |
+
"loss": 0.955,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5310119695321001,
|
| 434 |
+
"grad_norm": 1.546875,
|
| 435 |
+
"learning_rate": 4.739130434782609e-05,
|
| 436 |
+
"loss": 0.9521,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5397170837867247,
|
| 441 |
+
"grad_norm": 1.2578125,
|
| 442 |
+
"learning_rate": 4.734782608695652e-05,
|
| 443 |
+
"loss": 1.0155,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5484221980413493,
|
| 448 |
+
"grad_norm": 1.3125,
|
| 449 |
+
"learning_rate": 4.7304347826086956e-05,
|
| 450 |
+
"loss": 1.0093,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5571273122959739,
|
| 455 |
+
"grad_norm": 1.234375,
|
| 456 |
+
"learning_rate": 4.726086956521739e-05,
|
| 457 |
+
"loss": 0.8372,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5658324265505985,
|
| 462 |
+
"grad_norm": 1.0703125,
|
| 463 |
+
"learning_rate": 4.721739130434783e-05,
|
| 464 |
+
"loss": 0.8776,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5745375408052231,
|
| 469 |
+
"grad_norm": 1.2265625,
|
| 470 |
+
"learning_rate": 4.7173913043478264e-05,
|
| 471 |
+
"loss": 0.8854,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5832426550598476,
|
| 476 |
+
"grad_norm": 1.1171875,
|
| 477 |
+
"learning_rate": 4.71304347826087e-05,
|
| 478 |
+
"loss": 0.8966,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5919477693144722,
|
| 483 |
+
"grad_norm": 1.296875,
|
| 484 |
+
"learning_rate": 4.708695652173914e-05,
|
| 485 |
+
"loss": 0.9694,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6006528835690969,
|
| 490 |
+
"grad_norm": 1.1875,
|
| 491 |
+
"learning_rate": 4.7043478260869564e-05,
|
| 492 |
+
"loss": 1.062,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6093579978237215,
|
| 497 |
+
"grad_norm": 1.078125,
|
| 498 |
+
"learning_rate": 4.7e-05,
|
| 499 |
+
"loss": 0.8369,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6180631120783461,
|
| 504 |
+
"grad_norm": 1.1953125,
|
| 505 |
+
"learning_rate": 4.695652173913044e-05,
|
| 506 |
+
"loss": 0.7927,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6267682263329706,
|
| 511 |
+
"grad_norm": 1.4140625,
|
| 512 |
+
"learning_rate": 4.691304347826087e-05,
|
| 513 |
+
"loss": 1.3626,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6354733405875952,
|
| 518 |
+
"grad_norm": 1.1328125,
|
| 519 |
+
"learning_rate": 4.686956521739131e-05,
|
| 520 |
+
"loss": 0.7737,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6441784548422198,
|
| 525 |
+
"grad_norm": 1.0859375,
|
| 526 |
+
"learning_rate": 4.6826086956521745e-05,
|
| 527 |
+
"loss": 0.9044,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6528835690968444,
|
| 532 |
+
"grad_norm": 1.078125,
|
| 533 |
+
"learning_rate": 4.678260869565218e-05,
|
| 534 |
+
"loss": 0.9451,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.661588683351469,
|
| 539 |
+
"grad_norm": 1.234375,
|
| 540 |
+
"learning_rate": 4.673913043478261e-05,
|
| 541 |
+
"loss": 1.0073,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6702937976060935,
|
| 546 |
+
"grad_norm": 1.1484375,
|
| 547 |
+
"learning_rate": 4.6695652173913045e-05,
|
| 548 |
+
"loss": 1.0206,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6789989118607181,
|
| 553 |
+
"grad_norm": 1.25,
|
| 554 |
+
"learning_rate": 4.665217391304348e-05,
|
| 555 |
+
"loss": 0.7854,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6877040261153428,
|
| 560 |
+
"grad_norm": 1.0859375,
|
| 561 |
+
"learning_rate": 4.660869565217392e-05,
|
| 562 |
+
"loss": 0.9661,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6964091403699674,
|
| 567 |
+
"grad_norm": 1.296875,
|
| 568 |
+
"learning_rate": 4.656521739130435e-05,
|
| 569 |
+
"loss": 1.0657,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.705114254624592,
|
| 574 |
+
"grad_norm": 1.0390625,
|
| 575 |
+
"learning_rate": 4.6521739130434785e-05,
|
| 576 |
+
"loss": 0.6992,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7138193688792165,
|
| 581 |
+
"grad_norm": 1.0703125,
|
| 582 |
+
"learning_rate": 4.647826086956522e-05,
|
| 583 |
+
"loss": 0.8135,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7225244831338411,
|
| 588 |
+
"grad_norm": 1.359375,
|
| 589 |
+
"learning_rate": 4.643478260869565e-05,
|
| 590 |
+
"loss": 1.1033,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7312295973884657,
|
| 595 |
+
"grad_norm": 1.3828125,
|
| 596 |
+
"learning_rate": 4.6391304347826086e-05,
|
| 597 |
+
"loss": 0.8077,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7399347116430903,
|
| 602 |
+
"grad_norm": 1.0859375,
|
| 603 |
+
"learning_rate": 4.6347826086956526e-05,
|
| 604 |
+
"loss": 0.8582,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7486398258977149,
|
| 609 |
+
"grad_norm": 1.140625,
|
| 610 |
+
"learning_rate": 4.630434782608696e-05,
|
| 611 |
+
"loss": 1.0223,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7573449401523396,
|
| 616 |
+
"grad_norm": 1.2734375,
|
| 617 |
+
"learning_rate": 4.62608695652174e-05,
|
| 618 |
+
"loss": 0.7866,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.766050054406964,
|
| 623 |
+
"grad_norm": 1.1484375,
|
| 624 |
+
"learning_rate": 4.6217391304347826e-05,
|
| 625 |
+
"loss": 0.804,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7747551686615887,
|
| 630 |
+
"grad_norm": 0.96484375,
|
| 631 |
+
"learning_rate": 4.617391304347826e-05,
|
| 632 |
+
"loss": 0.681,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.7834602829162133,
|
| 637 |
+
"grad_norm": 1.0078125,
|
| 638 |
+
"learning_rate": 4.61304347826087e-05,
|
| 639 |
+
"loss": 0.9594,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7921653971708379,
|
| 644 |
+
"grad_norm": 1.0546875,
|
| 645 |
+
"learning_rate": 4.608695652173913e-05,
|
| 646 |
+
"loss": 0.9842,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8008705114254625,
|
| 651 |
+
"grad_norm": 1.09375,
|
| 652 |
+
"learning_rate": 4.6043478260869567e-05,
|
| 653 |
+
"loss": 0.9142,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.809575625680087,
|
| 658 |
+
"grad_norm": 1.15625,
|
| 659 |
+
"learning_rate": 4.600000000000001e-05,
|
| 660 |
+
"loss": 0.7379,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8182807399347116,
|
| 665 |
+
"grad_norm": 1.3984375,
|
| 666 |
+
"learning_rate": 4.595652173913044e-05,
|
| 667 |
+
"loss": 1.0656,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8269858541893362,
|
| 672 |
+
"grad_norm": 1.15625,
|
| 673 |
+
"learning_rate": 4.591304347826087e-05,
|
| 674 |
+
"loss": 0.9404,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8356909684439608,
|
| 679 |
+
"grad_norm": 1.109375,
|
| 680 |
+
"learning_rate": 4.586956521739131e-05,
|
| 681 |
+
"loss": 1.0705,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.8443960826985855,
|
| 686 |
+
"grad_norm": 1.1171875,
|
| 687 |
+
"learning_rate": 4.582608695652174e-05,
|
| 688 |
+
"loss": 1.1848,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.85310119695321,
|
| 693 |
+
"grad_norm": 1.15625,
|
| 694 |
+
"learning_rate": 4.5782608695652174e-05,
|
| 695 |
+
"loss": 0.8771,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8618063112078346,
|
| 700 |
+
"grad_norm": 1.265625,
|
| 701 |
+
"learning_rate": 4.5739130434782614e-05,
|
| 702 |
+
"loss": 0.9586,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8705114254624592,
|
| 707 |
+
"grad_norm": 1.1015625,
|
| 708 |
+
"learning_rate": 4.569565217391305e-05,
|
| 709 |
+
"loss": 0.7516,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.8792165397170838,
|
| 714 |
+
"grad_norm": 1.3125,
|
| 715 |
+
"learning_rate": 4.565217391304348e-05,
|
| 716 |
+
"loss": 0.8131,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8879216539717084,
|
| 721 |
+
"grad_norm": 1.109375,
|
| 722 |
+
"learning_rate": 4.5608695652173914e-05,
|
| 723 |
+
"loss": 0.9118,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8966267682263329,
|
| 728 |
+
"grad_norm": 1.4140625,
|
| 729 |
+
"learning_rate": 4.556521739130435e-05,
|
| 730 |
+
"loss": 0.8855,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.9053318824809575,
|
| 735 |
+
"grad_norm": 1.1796875,
|
| 736 |
+
"learning_rate": 4.552173913043479e-05,
|
| 737 |
+
"loss": 0.7721,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.9140369967355821,
|
| 742 |
+
"grad_norm": 1.2265625,
|
| 743 |
+
"learning_rate": 4.547826086956522e-05,
|
| 744 |
+
"loss": 0.7768,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9227421109902068,
|
| 749 |
+
"grad_norm": 1.0703125,
|
| 750 |
+
"learning_rate": 4.5434782608695655e-05,
|
| 751 |
+
"loss": 0.9557,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9314472252448314,
|
| 756 |
+
"grad_norm": 1.0625,
|
| 757 |
+
"learning_rate": 4.539130434782609e-05,
|
| 758 |
+
"loss": 0.8868,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.940152339499456,
|
| 763 |
+
"grad_norm": 1.15625,
|
| 764 |
+
"learning_rate": 4.534782608695652e-05,
|
| 765 |
+
"loss": 0.8889,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.9488574537540805,
|
| 770 |
+
"grad_norm": 1.15625,
|
| 771 |
+
"learning_rate": 4.5304347826086955e-05,
|
| 772 |
+
"loss": 1.1122,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9575625680087051,
|
| 777 |
+
"grad_norm": 1.1875,
|
| 778 |
+
"learning_rate": 4.5260869565217395e-05,
|
| 779 |
+
"loss": 0.7954,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.9662676822633297,
|
| 784 |
+
"grad_norm": 1.1796875,
|
| 785 |
+
"learning_rate": 4.521739130434783e-05,
|
| 786 |
+
"loss": 0.8551,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9749727965179543,
|
| 791 |
+
"grad_norm": 1.1953125,
|
| 792 |
+
"learning_rate": 4.517391304347826e-05,
|
| 793 |
+
"loss": 1.0285,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.9836779107725789,
|
| 798 |
+
"grad_norm": 1.25,
|
| 799 |
+
"learning_rate": 4.51304347826087e-05,
|
| 800 |
+
"loss": 1.0737,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9923830250272034,
|
| 805 |
+
"grad_norm": 1.015625,
|
| 806 |
+
"learning_rate": 4.508695652173913e-05,
|
| 807 |
+
"loss": 0.8448,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.0,
|
| 812 |
+
"grad_norm": 1.2421875,
|
| 813 |
+
"learning_rate": 4.504347826086956e-05,
|
| 814 |
+
"loss": 0.9171,
|
| 815 |
+
"step": 115
|
| 816 |
+
}
|
| 817 |
+
],
|
| 818 |
+
"logging_steps": 1,
|
| 819 |
+
"max_steps": 1150,
|
| 820 |
+
"num_input_tokens_seen": 0,
|
| 821 |
+
"num_train_epochs": 10,
|
| 822 |
+
"save_steps": 500,
|
| 823 |
+
"stateful_callbacks": {
|
| 824 |
+
"TrainerControl": {
|
| 825 |
+
"args": {
|
| 826 |
+
"should_epoch_stop": false,
|
| 827 |
+
"should_evaluate": false,
|
| 828 |
+
"should_log": false,
|
| 829 |
+
"should_save": true,
|
| 830 |
+
"should_training_stop": false
|
| 831 |
+
},
|
| 832 |
+
"attributes": {}
|
| 833 |
+
}
|
| 834 |
+
},
|
| 835 |
+
"total_flos": 5.91889867776983e+16,
|
| 836 |
+
"train_batch_size": 4,
|
| 837 |
+
"trial_name": null,
|
| 838 |
+
"trial_params": null
|
| 839 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9eb33b570a2d53cc411ba4cb3dd8961f6d08bd5390b1b0d416c95bd11ce4b6b
|
| 3 |
+
size 5905
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|