Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- checkpoint-1000/added_tokens.json +3 -0
- checkpoint-1000/chat_template.jinja +47 -0
- checkpoint-1000/config.json +110 -0
- checkpoint-1000/generation_config.json +13 -0
- checkpoint-1000/model-00001-of-00005.safetensors +3 -0
- checkpoint-1000/model-00002-of-00005.safetensors +3 -0
- checkpoint-1000/model-00003-of-00005.safetensors +3 -0
- checkpoint-1000/model-00004-of-00005.safetensors +3 -0
- checkpoint-1000/model-00005-of-00005.safetensors +3 -0
- checkpoint-1000/model.safetensors.index.json +0 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +33 -0
- checkpoint-1000/tokenizer.json +3 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +0 -0
- checkpoint-1000/trainer_state.json +1474 -0
- checkpoint-1000/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* 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 |
checkpoint-500/tokenizer.json 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 |
checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-1000/chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eoi_token_index": 256000,
|
| 9 |
+
"eos_token_id": 1,
|
| 10 |
+
"image_token_index": 262144,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"mm_tokens_per_image": 256,
|
| 13 |
+
"model_type": "gemma3",
|
| 14 |
+
"pad_token_id": 0,
|
| 15 |
+
"text_config": {
|
| 16 |
+
"_sliding_window_pattern": 6,
|
| 17 |
+
"attention_bias": false,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"attn_logit_softcapping": null,
|
| 20 |
+
"dtype": "bfloat16",
|
| 21 |
+
"final_logit_softcapping": null,
|
| 22 |
+
"head_dim": 256,
|
| 23 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 24 |
+
"hidden_size": 3840,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 15360,
|
| 27 |
+
"layer_types": [
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"sliding_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"sliding_attention",
|
| 68 |
+
"sliding_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"sliding_attention",
|
| 72 |
+
"sliding_attention",
|
| 73 |
+
"sliding_attention",
|
| 74 |
+
"sliding_attention",
|
| 75 |
+
"full_attention"
|
| 76 |
+
],
|
| 77 |
+
"max_position_embeddings": 131072,
|
| 78 |
+
"model_type": "gemma3_text",
|
| 79 |
+
"num_attention_heads": 16,
|
| 80 |
+
"num_hidden_layers": 48,
|
| 81 |
+
"num_key_value_heads": 8,
|
| 82 |
+
"query_pre_attn_scalar": 256,
|
| 83 |
+
"rms_norm_eps": 1e-06,
|
| 84 |
+
"rope_local_base_freq": 10000.0,
|
| 85 |
+
"rope_scaling": {
|
| 86 |
+
"factor": 8.0,
|
| 87 |
+
"rope_type": "linear"
|
| 88 |
+
},
|
| 89 |
+
"rope_theta": 1000000.0,
|
| 90 |
+
"sliding_window": 1024,
|
| 91 |
+
"use_cache": true,
|
| 92 |
+
"vocab_size": 262208
|
| 93 |
+
},
|
| 94 |
+
"transformers_version": "4.56.1",
|
| 95 |
+
"vision_config": {
|
| 96 |
+
"attention_dropout": 0.0,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1152,
|
| 100 |
+
"image_size": 896,
|
| 101 |
+
"intermediate_size": 4304,
|
| 102 |
+
"layer_norm_eps": 1e-06,
|
| 103 |
+
"model_type": "siglip_vision_model",
|
| 104 |
+
"num_attention_heads": 16,
|
| 105 |
+
"num_channels": 3,
|
| 106 |
+
"num_hidden_layers": 27,
|
| 107 |
+
"patch_size": 14,
|
| 108 |
+
"vision_use_head": false
|
| 109 |
+
}
|
| 110 |
+
}
|
checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.56.1"
|
| 13 |
+
}
|
checkpoint-1000/model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4847447e92599833e8dbaa3067cd201c3bb5c052efa91f11ba891e43234f7832
|
| 3 |
+
size 4979902192
|
checkpoint-1000/model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:891bd54eed03cba9ee1e705533a02a8217fcc29f356e4a1f53e5fd0d178883ad
|
| 3 |
+
size 4931296592
|
checkpoint-1000/model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c10e3154bd7d3d8d254e5b7b6373a80f21e02a8bcce985672b3ff3b8c96d517c
|
| 3 |
+
size 4931296656
|
checkpoint-1000/model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6e697636de59ca5074d326a56580537dae6dedb04d17a3506c59369e64cee97
|
| 3 |
+
size 4931296656
|
checkpoint-1000/model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e24902b5642443ba83a1b4cfd87d64626ba9b0bf98ed33e75448b3bb19c91b08
|
| 3 |
+
size 4601000928
|
checkpoint-1000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d38de383bc8806de503090ff6d0a0df438032045ea2a5b527675029ad497c1b5
|
| 3 |
+
size 14573116445
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f06901f6840e925dffc95a86f7539c99574a10a1ad53861a1e008efb8da651b
|
| 3 |
+
size 14645
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1047a716c066f9f4e78c42060834e4ca319f06029bfedda77528f4fcc6970b7e
|
| 3 |
+
size 1465
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
checkpoint-1000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-1000/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,1474 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.0975568080320954,
|
| 14 |
+
"epoch": 0.004,
|
| 15 |
+
"grad_norm": 1928.0,
|
| 16 |
+
"learning_rate": 4.5000000000000003e-07,
|
| 17 |
+
"loss": 51.036,
|
| 18 |
+
"mean_token_accuracy": 0.5464097319170833,
|
| 19 |
+
"num_tokens": 51831.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.2103175908327102,
|
| 24 |
+
"epoch": 0.008,
|
| 25 |
+
"grad_norm": 1012.0,
|
| 26 |
+
"learning_rate": 9.500000000000001e-07,
|
| 27 |
+
"loss": 47.7535,
|
| 28 |
+
"mean_token_accuracy": 0.549801179766655,
|
| 29 |
+
"num_tokens": 103172.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.4519254021346568,
|
| 34 |
+
"epoch": 0.012,
|
| 35 |
+
"grad_norm": 1024.0,
|
| 36 |
+
"learning_rate": 1.45e-06,
|
| 37 |
+
"loss": 45.5399,
|
| 38 |
+
"mean_token_accuracy": 0.5487965773791075,
|
| 39 |
+
"num_tokens": 147915.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.515171455964446,
|
| 44 |
+
"epoch": 0.016,
|
| 45 |
+
"grad_norm": 440.0,
|
| 46 |
+
"learning_rate": 1.9500000000000004e-06,
|
| 47 |
+
"loss": 40.0298,
|
| 48 |
+
"mean_token_accuracy": 0.5707932172343135,
|
| 49 |
+
"num_tokens": 195524.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 1.529548142105341,
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"grad_norm": 328.0,
|
| 56 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 57 |
+
"loss": 33.3046,
|
| 58 |
+
"mean_token_accuracy": 0.5914752574637532,
|
| 59 |
+
"num_tokens": 243747.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 1.5671692434698343,
|
| 64 |
+
"epoch": 0.024,
|
| 65 |
+
"grad_norm": 241.0,
|
| 66 |
+
"learning_rate": 2.95e-06,
|
| 67 |
+
"loss": 30.3037,
|
| 68 |
+
"mean_token_accuracy": 0.6058902809396386,
|
| 69 |
+
"num_tokens": 296999.0,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.549248830974102,
|
| 74 |
+
"epoch": 0.028,
|
| 75 |
+
"grad_norm": 235.0,
|
| 76 |
+
"learning_rate": 3.45e-06,
|
| 77 |
+
"loss": 29.0295,
|
| 78 |
+
"mean_token_accuracy": 0.6220679895952343,
|
| 79 |
+
"num_tokens": 342114.0,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 1.42005056142807,
|
| 84 |
+
"epoch": 0.032,
|
| 85 |
+
"grad_norm": 167.0,
|
| 86 |
+
"learning_rate": 3.95e-06,
|
| 87 |
+
"loss": 26.6089,
|
| 88 |
+
"mean_token_accuracy": 0.6380933992564678,
|
| 89 |
+
"num_tokens": 390903.0,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.5127948723733424,
|
| 94 |
+
"epoch": 0.036,
|
| 95 |
+
"grad_norm": 167.0,
|
| 96 |
+
"learning_rate": 4.450000000000001e-06,
|
| 97 |
+
"loss": 24.8172,
|
| 98 |
+
"mean_token_accuracy": 0.6465719180181623,
|
| 99 |
+
"num_tokens": 440359.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.5200586583465339,
|
| 104 |
+
"epoch": 0.04,
|
| 105 |
+
"grad_norm": 142.0,
|
| 106 |
+
"learning_rate": 4.95e-06,
|
| 107 |
+
"loss": 24.207,
|
| 108 |
+
"mean_token_accuracy": 0.6497391745448112,
|
| 109 |
+
"num_tokens": 488481.0,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.04,
|
| 114 |
+
"eval_biology_entropy": 1.4843950763940812,
|
| 115 |
+
"eval_biology_loss": 1.4266694784164429,
|
| 116 |
+
"eval_biology_mean_token_accuracy": 0.6619762739539147,
|
| 117 |
+
"eval_biology_num_tokens": 488481.0,
|
| 118 |
+
"eval_biology_runtime": 36.5287,
|
| 119 |
+
"eval_biology_samples_per_second": 13.688,
|
| 120 |
+
"eval_biology_steps_per_second": 13.688,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"eval_chemistry_entropy": 1.091414896786213,
|
| 126 |
+
"eval_chemistry_loss": 1.0560342073440552,
|
| 127 |
+
"eval_chemistry_mean_token_accuracy": 0.7318743930459023,
|
| 128 |
+
"eval_chemistry_num_tokens": 488481.0,
|
| 129 |
+
"eval_chemistry_runtime": 39.96,
|
| 130 |
+
"eval_chemistry_samples_per_second": 12.513,
|
| 131 |
+
"eval_chemistry_steps_per_second": 12.513,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.04,
|
| 136 |
+
"eval_math_entropy": 0.9103146089911461,
|
| 137 |
+
"eval_math_loss": 1.0316376686096191,
|
| 138 |
+
"eval_math_mean_token_accuracy": 0.7397149602174758,
|
| 139 |
+
"eval_math_num_tokens": 488481.0,
|
| 140 |
+
"eval_math_runtime": 41.0822,
|
| 141 |
+
"eval_math_samples_per_second": 12.171,
|
| 142 |
+
"eval_math_steps_per_second": 12.171,
|
| 143 |
+
"step": 100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.04,
|
| 147 |
+
"eval_physics_entropy": 0.9860039167404174,
|
| 148 |
+
"eval_physics_loss": 0.9796567559242249,
|
| 149 |
+
"eval_physics_mean_token_accuracy": 0.7483667035698891,
|
| 150 |
+
"eval_physics_num_tokens": 488481.0,
|
| 151 |
+
"eval_physics_runtime": 45.3249,
|
| 152 |
+
"eval_physics_samples_per_second": 11.031,
|
| 153 |
+
"eval_physics_steps_per_second": 11.031,
|
| 154 |
+
"step": 100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"entropy": 1.444656402617693,
|
| 158 |
+
"epoch": 0.044,
|
| 159 |
+
"grad_norm": 121.0,
|
| 160 |
+
"learning_rate": 5.450000000000001e-06,
|
| 161 |
+
"loss": 22.4665,
|
| 162 |
+
"mean_token_accuracy": 0.6580426702275872,
|
| 163 |
+
"num_tokens": 537471.0,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"entropy": 1.3339354760944844,
|
| 168 |
+
"epoch": 0.048,
|
| 169 |
+
"grad_norm": 129.0,
|
| 170 |
+
"learning_rate": 5.950000000000001e-06,
|
| 171 |
+
"loss": 21.4085,
|
| 172 |
+
"mean_token_accuracy": 0.6670540764927864,
|
| 173 |
+
"num_tokens": 589868.0,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"entropy": 1.3668562419712544,
|
| 178 |
+
"epoch": 0.052,
|
| 179 |
+
"grad_norm": 124.5,
|
| 180 |
+
"learning_rate": 6.450000000000001e-06,
|
| 181 |
+
"loss": 21.7438,
|
| 182 |
+
"mean_token_accuracy": 0.6594993283972144,
|
| 183 |
+
"num_tokens": 639512.0,
|
| 184 |
+
"step": 130
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"entropy": 1.3065196067094802,
|
| 188 |
+
"epoch": 0.056,
|
| 189 |
+
"grad_norm": 118.5,
|
| 190 |
+
"learning_rate": 6.95e-06,
|
| 191 |
+
"loss": 20.9541,
|
| 192 |
+
"mean_token_accuracy": 0.6683343779295683,
|
| 193 |
+
"num_tokens": 690754.0,
|
| 194 |
+
"step": 140
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"entropy": 1.3160824533551931,
|
| 198 |
+
"epoch": 0.06,
|
| 199 |
+
"grad_norm": 115.5,
|
| 200 |
+
"learning_rate": 7.450000000000001e-06,
|
| 201 |
+
"loss": 21.525,
|
| 202 |
+
"mean_token_accuracy": 0.664486956782639,
|
| 203 |
+
"num_tokens": 737075.0,
|
| 204 |
+
"step": 150
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"entropy": 1.3052487019449472,
|
| 208 |
+
"epoch": 0.064,
|
| 209 |
+
"grad_norm": 113.0,
|
| 210 |
+
"learning_rate": 7.950000000000002e-06,
|
| 211 |
+
"loss": 20.5473,
|
| 212 |
+
"mean_token_accuracy": 0.672793828509748,
|
| 213 |
+
"num_tokens": 791190.0,
|
| 214 |
+
"step": 160
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"entropy": 1.29992272593081,
|
| 218 |
+
"epoch": 0.068,
|
| 219 |
+
"grad_norm": 100.0,
|
| 220 |
+
"learning_rate": 8.45e-06,
|
| 221 |
+
"loss": 21.0557,
|
| 222 |
+
"mean_token_accuracy": 0.6683677529916168,
|
| 223 |
+
"num_tokens": 841344.0,
|
| 224 |
+
"step": 170
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"entropy": 1.3232017546892165,
|
| 228 |
+
"epoch": 0.072,
|
| 229 |
+
"grad_norm": 114.5,
|
| 230 |
+
"learning_rate": 8.95e-06,
|
| 231 |
+
"loss": 21.0887,
|
| 232 |
+
"mean_token_accuracy": 0.6686861604452133,
|
| 233 |
+
"num_tokens": 890075.0,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"entropy": 1.2425255428999662,
|
| 238 |
+
"epoch": 0.076,
|
| 239 |
+
"grad_norm": 106.0,
|
| 240 |
+
"learning_rate": 9.450000000000001e-06,
|
| 241 |
+
"loss": 19.9137,
|
| 242 |
+
"mean_token_accuracy": 0.6810434710234403,
|
| 243 |
+
"num_tokens": 940599.0,
|
| 244 |
+
"step": 190
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"entropy": 1.256486358679831,
|
| 248 |
+
"epoch": 0.08,
|
| 249 |
+
"grad_norm": 117.5,
|
| 250 |
+
"learning_rate": 9.950000000000001e-06,
|
| 251 |
+
"loss": 20.0961,
|
| 252 |
+
"mean_token_accuracy": 0.6819845270365477,
|
| 253 |
+
"num_tokens": 989860.0,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.08,
|
| 258 |
+
"eval_biology_entropy": 1.241776801943779,
|
| 259 |
+
"eval_biology_loss": 1.2506648302078247,
|
| 260 |
+
"eval_biology_mean_token_accuracy": 0.6855908244848251,
|
| 261 |
+
"eval_biology_num_tokens": 989860.0,
|
| 262 |
+
"eval_biology_runtime": 36.0247,
|
| 263 |
+
"eval_biology_samples_per_second": 13.879,
|
| 264 |
+
"eval_biology_steps_per_second": 13.879,
|
| 265 |
+
"step": 200
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.08,
|
| 269 |
+
"eval_chemistry_entropy": 0.9190568276047707,
|
| 270 |
+
"eval_chemistry_loss": 0.9248532652854919,
|
| 271 |
+
"eval_chemistry_mean_token_accuracy": 0.7533808985352516,
|
| 272 |
+
"eval_chemistry_num_tokens": 989860.0,
|
| 273 |
+
"eval_chemistry_runtime": 40.487,
|
| 274 |
+
"eval_chemistry_samples_per_second": 12.35,
|
| 275 |
+
"eval_chemistry_steps_per_second": 12.35,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.08,
|
| 280 |
+
"eval_math_entropy": 0.7673128904104233,
|
| 281 |
+
"eval_math_loss": 0.9293037056922913,
|
| 282 |
+
"eval_math_mean_token_accuracy": 0.759642232298851,
|
| 283 |
+
"eval_math_num_tokens": 989860.0,
|
| 284 |
+
"eval_math_runtime": 41.5439,
|
| 285 |
+
"eval_math_samples_per_second": 12.035,
|
| 286 |
+
"eval_math_steps_per_second": 12.035,
|
| 287 |
+
"step": 200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.08,
|
| 291 |
+
"eval_physics_entropy": 0.8287813304066658,
|
| 292 |
+
"eval_physics_loss": 0.8567265868186951,
|
| 293 |
+
"eval_physics_mean_token_accuracy": 0.770364968419075,
|
| 294 |
+
"eval_physics_num_tokens": 989860.0,
|
| 295 |
+
"eval_physics_runtime": 46.6277,
|
| 296 |
+
"eval_physics_samples_per_second": 10.723,
|
| 297 |
+
"eval_physics_steps_per_second": 10.723,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"entropy": 1.2084858063608408,
|
| 302 |
+
"epoch": 0.084,
|
| 303 |
+
"grad_norm": 99.5,
|
| 304 |
+
"learning_rate": 1.045e-05,
|
| 305 |
+
"loss": 19.469,
|
| 306 |
+
"mean_token_accuracy": 0.6908657155930996,
|
| 307 |
+
"num_tokens": 1041199.0,
|
| 308 |
+
"step": 210
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"entropy": 1.3143941588699817,
|
| 312 |
+
"epoch": 0.088,
|
| 313 |
+
"grad_norm": 139.0,
|
| 314 |
+
"learning_rate": 1.095e-05,
|
| 315 |
+
"loss": 21.209,
|
| 316 |
+
"mean_token_accuracy": 0.670545787923038,
|
| 317 |
+
"num_tokens": 1087099.0,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"entropy": 1.2587614998221397,
|
| 322 |
+
"epoch": 0.092,
|
| 323 |
+
"grad_norm": 108.0,
|
| 324 |
+
"learning_rate": 1.145e-05,
|
| 325 |
+
"loss": 20.1256,
|
| 326 |
+
"mean_token_accuracy": 0.6842886801809073,
|
| 327 |
+
"num_tokens": 1135090.0,
|
| 328 |
+
"step": 230
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"entropy": 1.2565513662993908,
|
| 332 |
+
"epoch": 0.096,
|
| 333 |
+
"grad_norm": 106.0,
|
| 334 |
+
"learning_rate": 1.195e-05,
|
| 335 |
+
"loss": 20.4044,
|
| 336 |
+
"mean_token_accuracy": 0.6776034630835056,
|
| 337 |
+
"num_tokens": 1181777.0,
|
| 338 |
+
"step": 240
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"entropy": 1.2938017453998327,
|
| 342 |
+
"epoch": 0.1,
|
| 343 |
+
"grad_norm": 112.0,
|
| 344 |
+
"learning_rate": 1.2450000000000003e-05,
|
| 345 |
+
"loss": 20.3714,
|
| 346 |
+
"mean_token_accuracy": 0.6780621778219939,
|
| 347 |
+
"num_tokens": 1229242.0,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"entropy": 1.2320711638778448,
|
| 352 |
+
"epoch": 0.104,
|
| 353 |
+
"grad_norm": 94.5,
|
| 354 |
+
"learning_rate": 1.295e-05,
|
| 355 |
+
"loss": 20.052,
|
| 356 |
+
"mean_token_accuracy": 0.6799502000212669,
|
| 357 |
+
"num_tokens": 1283881.0,
|
| 358 |
+
"step": 260
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"entropy": 1.2415869060903788,
|
| 362 |
+
"epoch": 0.108,
|
| 363 |
+
"grad_norm": 107.0,
|
| 364 |
+
"learning_rate": 1.3450000000000002e-05,
|
| 365 |
+
"loss": 19.9151,
|
| 366 |
+
"mean_token_accuracy": 0.6853171430528164,
|
| 367 |
+
"num_tokens": 1332507.0,
|
| 368 |
+
"step": 270
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"entropy": 1.242128773033619,
|
| 372 |
+
"epoch": 0.112,
|
| 373 |
+
"grad_norm": 92.5,
|
| 374 |
+
"learning_rate": 1.3950000000000002e-05,
|
| 375 |
+
"loss": 19.9203,
|
| 376 |
+
"mean_token_accuracy": 0.685390866547823,
|
| 377 |
+
"num_tokens": 1385513.0,
|
| 378 |
+
"step": 280
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"entropy": 1.2662223283201457,
|
| 382 |
+
"epoch": 0.116,
|
| 383 |
+
"grad_norm": 100.5,
|
| 384 |
+
"learning_rate": 1.4450000000000002e-05,
|
| 385 |
+
"loss": 20.3929,
|
| 386 |
+
"mean_token_accuracy": 0.6766710925847292,
|
| 387 |
+
"num_tokens": 1432251.0,
|
| 388 |
+
"step": 290
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"entropy": 1.198459953069687,
|
| 392 |
+
"epoch": 0.12,
|
| 393 |
+
"grad_norm": 101.0,
|
| 394 |
+
"learning_rate": 1.4950000000000003e-05,
|
| 395 |
+
"loss": 19.3584,
|
| 396 |
+
"mean_token_accuracy": 0.68702756986022,
|
| 397 |
+
"num_tokens": 1483667.0,
|
| 398 |
+
"step": 300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.12,
|
| 402 |
+
"eval_biology_entropy": 1.2469175053834916,
|
| 403 |
+
"eval_biology_loss": 1.2332121133804321,
|
| 404 |
+
"eval_biology_mean_token_accuracy": 0.6868851281404496,
|
| 405 |
+
"eval_biology_num_tokens": 1483667.0,
|
| 406 |
+
"eval_biology_runtime": 36.8445,
|
| 407 |
+
"eval_biology_samples_per_second": 13.571,
|
| 408 |
+
"eval_biology_steps_per_second": 13.571,
|
| 409 |
+
"step": 300
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.12,
|
| 413 |
+
"eval_chemistry_entropy": 0.9295264416337014,
|
| 414 |
+
"eval_chemistry_loss": 0.9073873162269592,
|
| 415 |
+
"eval_chemistry_mean_token_accuracy": 0.7570922123789787,
|
| 416 |
+
"eval_chemistry_num_tokens": 1483667.0,
|
| 417 |
+
"eval_chemistry_runtime": 40.4179,
|
| 418 |
+
"eval_chemistry_samples_per_second": 12.371,
|
| 419 |
+
"eval_chemistry_steps_per_second": 12.371,
|
| 420 |
+
"step": 300
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.12,
|
| 424 |
+
"eval_math_entropy": 0.7820550892949104,
|
| 425 |
+
"eval_math_loss": 0.9024779200553894,
|
| 426 |
+
"eval_math_mean_token_accuracy": 0.7648742213249207,
|
| 427 |
+
"eval_math_num_tokens": 1483667.0,
|
| 428 |
+
"eval_math_runtime": 41.3487,
|
| 429 |
+
"eval_math_samples_per_second": 12.092,
|
| 430 |
+
"eval_math_steps_per_second": 12.092,
|
| 431 |
+
"step": 300
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.12,
|
| 435 |
+
"eval_physics_entropy": 0.8381168316006661,
|
| 436 |
+
"eval_physics_loss": 0.8357300758361816,
|
| 437 |
+
"eval_physics_mean_token_accuracy": 0.7741321437358856,
|
| 438 |
+
"eval_physics_num_tokens": 1483667.0,
|
| 439 |
+
"eval_physics_runtime": 46.0597,
|
| 440 |
+
"eval_physics_samples_per_second": 10.855,
|
| 441 |
+
"eval_physics_steps_per_second": 10.855,
|
| 442 |
+
"step": 300
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"entropy": 1.268108993396163,
|
| 446 |
+
"epoch": 0.124,
|
| 447 |
+
"grad_norm": 87.0,
|
| 448 |
+
"learning_rate": 1.545e-05,
|
| 449 |
+
"loss": 20.169,
|
| 450 |
+
"mean_token_accuracy": 0.6794606490060687,
|
| 451 |
+
"num_tokens": 1534286.0,
|
| 452 |
+
"step": 310
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"entropy": 1.2664785664528608,
|
| 456 |
+
"epoch": 0.128,
|
| 457 |
+
"grad_norm": 95.0,
|
| 458 |
+
"learning_rate": 1.595e-05,
|
| 459 |
+
"loss": 20.1543,
|
| 460 |
+
"mean_token_accuracy": 0.6814448466524482,
|
| 461 |
+
"num_tokens": 1582368.0,
|
| 462 |
+
"step": 320
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"entropy": 1.2443583220243455,
|
| 466 |
+
"epoch": 0.132,
|
| 467 |
+
"grad_norm": 100.5,
|
| 468 |
+
"learning_rate": 1.645e-05,
|
| 469 |
+
"loss": 20.1453,
|
| 470 |
+
"mean_token_accuracy": 0.6805377397686243,
|
| 471 |
+
"num_tokens": 1630878.0,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"entropy": 1.295349196344614,
|
| 476 |
+
"epoch": 0.136,
|
| 477 |
+
"grad_norm": 84.5,
|
| 478 |
+
"learning_rate": 1.6950000000000002e-05,
|
| 479 |
+
"loss": 20.5474,
|
| 480 |
+
"mean_token_accuracy": 0.6783911313861608,
|
| 481 |
+
"num_tokens": 1677060.0,
|
| 482 |
+
"step": 340
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"entropy": 1.2136471576988697,
|
| 486 |
+
"epoch": 0.14,
|
| 487 |
+
"grad_norm": 96.0,
|
| 488 |
+
"learning_rate": 1.7450000000000004e-05,
|
| 489 |
+
"loss": 19.7364,
|
| 490 |
+
"mean_token_accuracy": 0.6849099691957236,
|
| 491 |
+
"num_tokens": 1725186.0,
|
| 492 |
+
"step": 350
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"entropy": 1.2611235719174148,
|
| 496 |
+
"epoch": 0.144,
|
| 497 |
+
"grad_norm": 96.5,
|
| 498 |
+
"learning_rate": 1.795e-05,
|
| 499 |
+
"loss": 20.2599,
|
| 500 |
+
"mean_token_accuracy": 0.6779890628531575,
|
| 501 |
+
"num_tokens": 1773764.0,
|
| 502 |
+
"step": 360
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"entropy": 1.24961077272892,
|
| 506 |
+
"epoch": 0.148,
|
| 507 |
+
"grad_norm": 93.0,
|
| 508 |
+
"learning_rate": 1.845e-05,
|
| 509 |
+
"loss": 19.9901,
|
| 510 |
+
"mean_token_accuracy": 0.6829751830548048,
|
| 511 |
+
"num_tokens": 1823706.0,
|
| 512 |
+
"step": 370
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"entropy": 1.2856210090219975,
|
| 516 |
+
"epoch": 0.152,
|
| 517 |
+
"grad_norm": 103.5,
|
| 518 |
+
"learning_rate": 1.8950000000000003e-05,
|
| 519 |
+
"loss": 20.5301,
|
| 520 |
+
"mean_token_accuracy": 0.6794548545032739,
|
| 521 |
+
"num_tokens": 1873167.0,
|
| 522 |
+
"step": 380
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"entropy": 1.28184983022511,
|
| 526 |
+
"epoch": 0.156,
|
| 527 |
+
"grad_norm": 87.5,
|
| 528 |
+
"learning_rate": 1.9450000000000002e-05,
|
| 529 |
+
"loss": 20.4718,
|
| 530 |
+
"mean_token_accuracy": 0.6774068776518106,
|
| 531 |
+
"num_tokens": 1921484.0,
|
| 532 |
+
"step": 390
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"entropy": 1.2587715853005648,
|
| 536 |
+
"epoch": 0.16,
|
| 537 |
+
"grad_norm": 90.5,
|
| 538 |
+
"learning_rate": 1.9950000000000004e-05,
|
| 539 |
+
"loss": 20.2765,
|
| 540 |
+
"mean_token_accuracy": 0.6795550292357803,
|
| 541 |
+
"num_tokens": 1970077.0,
|
| 542 |
+
"step": 400
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.16,
|
| 546 |
+
"eval_biology_entropy": 1.2585812546014785,
|
| 547 |
+
"eval_biology_loss": 1.2385821342468262,
|
| 548 |
+
"eval_biology_mean_token_accuracy": 0.6883087210059166,
|
| 549 |
+
"eval_biology_num_tokens": 1970077.0,
|
| 550 |
+
"eval_biology_runtime": 40.6484,
|
| 551 |
+
"eval_biology_samples_per_second": 12.301,
|
| 552 |
+
"eval_biology_steps_per_second": 12.301,
|
| 553 |
+
"step": 400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.16,
|
| 557 |
+
"eval_chemistry_entropy": 0.9248176854848862,
|
| 558 |
+
"eval_chemistry_loss": 0.9106165766716003,
|
| 559 |
+
"eval_chemistry_mean_token_accuracy": 0.7573499709963799,
|
| 560 |
+
"eval_chemistry_num_tokens": 1970077.0,
|
| 561 |
+
"eval_chemistry_runtime": 40.4652,
|
| 562 |
+
"eval_chemistry_samples_per_second": 12.356,
|
| 563 |
+
"eval_chemistry_steps_per_second": 12.356,
|
| 564 |
+
"step": 400
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.16,
|
| 568 |
+
"eval_math_entropy": 0.7678850111961365,
|
| 569 |
+
"eval_math_loss": 0.897013783454895,
|
| 570 |
+
"eval_math_mean_token_accuracy": 0.7673858489990234,
|
| 571 |
+
"eval_math_num_tokens": 1970077.0,
|
| 572 |
+
"eval_math_runtime": 41.3756,
|
| 573 |
+
"eval_math_samples_per_second": 12.084,
|
| 574 |
+
"eval_math_steps_per_second": 12.084,
|
| 575 |
+
"step": 400
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.16,
|
| 579 |
+
"eval_physics_entropy": 0.8230015668869018,
|
| 580 |
+
"eval_physics_loss": 0.8317809104919434,
|
| 581 |
+
"eval_physics_mean_token_accuracy": 0.7749597446918488,
|
| 582 |
+
"eval_physics_num_tokens": 1970077.0,
|
| 583 |
+
"eval_physics_runtime": 45.5271,
|
| 584 |
+
"eval_physics_samples_per_second": 10.982,
|
| 585 |
+
"eval_physics_steps_per_second": 10.982,
|
| 586 |
+
"step": 400
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 1.2881209932267665,
|
| 590 |
+
"epoch": 0.164,
|
| 591 |
+
"grad_norm": 80.5,
|
| 592 |
+
"learning_rate": 1.9950000000000004e-05,
|
| 593 |
+
"loss": 20.7614,
|
| 594 |
+
"mean_token_accuracy": 0.6718229403719306,
|
| 595 |
+
"num_tokens": 2019053.0,
|
| 596 |
+
"step": 410
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 1.2165789466351271,
|
| 600 |
+
"epoch": 0.168,
|
| 601 |
+
"grad_norm": 75.5,
|
| 602 |
+
"learning_rate": 1.9894444444444446e-05,
|
| 603 |
+
"loss": 19.5986,
|
| 604 |
+
"mean_token_accuracy": 0.6869289472699165,
|
| 605 |
+
"num_tokens": 2066815.0,
|
| 606 |
+
"step": 420
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 1.2494619188830256,
|
| 610 |
+
"epoch": 0.172,
|
| 611 |
+
"grad_norm": 80.5,
|
| 612 |
+
"learning_rate": 1.983888888888889e-05,
|
| 613 |
+
"loss": 20.2759,
|
| 614 |
+
"mean_token_accuracy": 0.6808055322617292,
|
| 615 |
+
"num_tokens": 2116402.0,
|
| 616 |
+
"step": 430
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 1.214642644301057,
|
| 620 |
+
"epoch": 0.176,
|
| 621 |
+
"grad_norm": 81.5,
|
| 622 |
+
"learning_rate": 1.9783333333333334e-05,
|
| 623 |
+
"loss": 19.3769,
|
| 624 |
+
"mean_token_accuracy": 0.6881225043907762,
|
| 625 |
+
"num_tokens": 2168354.0,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 1.2326878625899553,
|
| 630 |
+
"epoch": 0.18,
|
| 631 |
+
"grad_norm": 76.0,
|
| 632 |
+
"learning_rate": 1.972777777777778e-05,
|
| 633 |
+
"loss": 20.0507,
|
| 634 |
+
"mean_token_accuracy": 0.6823928710073233,
|
| 635 |
+
"num_tokens": 2219158.0,
|
| 636 |
+
"step": 450
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 1.2790402939543128,
|
| 640 |
+
"epoch": 0.184,
|
| 641 |
+
"grad_norm": 97.0,
|
| 642 |
+
"learning_rate": 1.9672222222222222e-05,
|
| 643 |
+
"loss": 20.4576,
|
| 644 |
+
"mean_token_accuracy": 0.6788654251024127,
|
| 645 |
+
"num_tokens": 2270617.0,
|
| 646 |
+
"step": 460
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 1.2233176242560149,
|
| 650 |
+
"epoch": 0.188,
|
| 651 |
+
"grad_norm": 76.0,
|
| 652 |
+
"learning_rate": 1.9616666666666668e-05,
|
| 653 |
+
"loss": 19.4471,
|
| 654 |
+
"mean_token_accuracy": 0.6852962577715516,
|
| 655 |
+
"num_tokens": 2322034.0,
|
| 656 |
+
"step": 470
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 1.284807311743498,
|
| 660 |
+
"epoch": 0.192,
|
| 661 |
+
"grad_norm": 97.0,
|
| 662 |
+
"learning_rate": 1.9561111111111114e-05,
|
| 663 |
+
"loss": 21.2325,
|
| 664 |
+
"mean_token_accuracy": 0.6681901682168245,
|
| 665 |
+
"num_tokens": 2365822.0,
|
| 666 |
+
"step": 480
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"entropy": 1.250083539262414,
|
| 670 |
+
"epoch": 0.196,
|
| 671 |
+
"grad_norm": 93.5,
|
| 672 |
+
"learning_rate": 1.9505555555555556e-05,
|
| 673 |
+
"loss": 19.6203,
|
| 674 |
+
"mean_token_accuracy": 0.6853536464273929,
|
| 675 |
+
"num_tokens": 2413853.0,
|
| 676 |
+
"step": 490
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"entropy": 1.2981292121112347,
|
| 680 |
+
"epoch": 0.2,
|
| 681 |
+
"grad_norm": 85.0,
|
| 682 |
+
"learning_rate": 1.9450000000000002e-05,
|
| 683 |
+
"loss": 20.8012,
|
| 684 |
+
"mean_token_accuracy": 0.6707905715331435,
|
| 685 |
+
"num_tokens": 2459876.0,
|
| 686 |
+
"step": 500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.2,
|
| 690 |
+
"eval_biology_entropy": 1.2485336683392525,
|
| 691 |
+
"eval_biology_loss": 1.2281557321548462,
|
| 692 |
+
"eval_biology_mean_token_accuracy": 0.6897270123958588,
|
| 693 |
+
"eval_biology_num_tokens": 2459876.0,
|
| 694 |
+
"eval_biology_runtime": 38.8945,
|
| 695 |
+
"eval_biology_samples_per_second": 12.855,
|
| 696 |
+
"eval_biology_steps_per_second": 12.855,
|
| 697 |
+
"step": 500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.2,
|
| 701 |
+
"eval_chemistry_entropy": 0.9259556359648704,
|
| 702 |
+
"eval_chemistry_loss": 0.9128974676132202,
|
| 703 |
+
"eval_chemistry_mean_token_accuracy": 0.7565669685602188,
|
| 704 |
+
"eval_chemistry_num_tokens": 2459876.0,
|
| 705 |
+
"eval_chemistry_runtime": 40.516,
|
| 706 |
+
"eval_chemistry_samples_per_second": 12.341,
|
| 707 |
+
"eval_chemistry_steps_per_second": 12.341,
|
| 708 |
+
"step": 500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.2,
|
| 712 |
+
"eval_math_entropy": 0.7720121605396271,
|
| 713 |
+
"eval_math_loss": 0.9020798206329346,
|
| 714 |
+
"eval_math_mean_token_accuracy": 0.7660462435483932,
|
| 715 |
+
"eval_math_num_tokens": 2459876.0,
|
| 716 |
+
"eval_math_runtime": 62.8982,
|
| 717 |
+
"eval_math_samples_per_second": 7.949,
|
| 718 |
+
"eval_math_steps_per_second": 7.949,
|
| 719 |
+
"step": 500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.2,
|
| 723 |
+
"eval_physics_entropy": 0.8241469451785087,
|
| 724 |
+
"eval_physics_loss": 0.832719624042511,
|
| 725 |
+
"eval_physics_mean_token_accuracy": 0.7746937532424927,
|
| 726 |
+
"eval_physics_num_tokens": 2459876.0,
|
| 727 |
+
"eval_physics_runtime": 76.8817,
|
| 728 |
+
"eval_physics_samples_per_second": 6.504,
|
| 729 |
+
"eval_physics_steps_per_second": 6.504,
|
| 730 |
+
"step": 500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 1.2163557052612304,
|
| 734 |
+
"epoch": 0.204,
|
| 735 |
+
"grad_norm": 73.5,
|
| 736 |
+
"learning_rate": 1.9394444444444448e-05,
|
| 737 |
+
"loss": 19.9923,
|
| 738 |
+
"mean_token_accuracy": 0.6821251731365919,
|
| 739 |
+
"num_tokens": 2509187.0,
|
| 740 |
+
"step": 510
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 1.2736122459173203,
|
| 744 |
+
"epoch": 0.208,
|
| 745 |
+
"grad_norm": 88.5,
|
| 746 |
+
"learning_rate": 1.933888888888889e-05,
|
| 747 |
+
"loss": 20.2436,
|
| 748 |
+
"mean_token_accuracy": 0.6758794913068413,
|
| 749 |
+
"num_tokens": 2558762.0,
|
| 750 |
+
"step": 520
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 1.2216465022414922,
|
| 754 |
+
"epoch": 0.212,
|
| 755 |
+
"grad_norm": 71.5,
|
| 756 |
+
"learning_rate": 1.9283333333333332e-05,
|
| 757 |
+
"loss": 19.6407,
|
| 758 |
+
"mean_token_accuracy": 0.6855740923434496,
|
| 759 |
+
"num_tokens": 2608616.0,
|
| 760 |
+
"step": 530
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 1.2674344064667822,
|
| 764 |
+
"epoch": 0.216,
|
| 765 |
+
"grad_norm": 86.0,
|
| 766 |
+
"learning_rate": 1.9227777777777778e-05,
|
| 767 |
+
"loss": 20.4517,
|
| 768 |
+
"mean_token_accuracy": 0.6805386714637279,
|
| 769 |
+
"num_tokens": 2654953.0,
|
| 770 |
+
"step": 540
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 1.2348025966435672,
|
| 774 |
+
"epoch": 0.22,
|
| 775 |
+
"grad_norm": 79.5,
|
| 776 |
+
"learning_rate": 1.9172222222222224e-05,
|
| 777 |
+
"loss": 19.9027,
|
| 778 |
+
"mean_token_accuracy": 0.6820508353412151,
|
| 779 |
+
"num_tokens": 2704686.0,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 1.2361498434096574,
|
| 784 |
+
"epoch": 0.224,
|
| 785 |
+
"grad_norm": 86.5,
|
| 786 |
+
"learning_rate": 1.911666666666667e-05,
|
| 787 |
+
"loss": 20.0735,
|
| 788 |
+
"mean_token_accuracy": 0.6846253119409085,
|
| 789 |
+
"num_tokens": 2755347.0,
|
| 790 |
+
"step": 560
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 1.2503492299467325,
|
| 794 |
+
"epoch": 0.228,
|
| 795 |
+
"grad_norm": 77.0,
|
| 796 |
+
"learning_rate": 1.9061111111111112e-05,
|
| 797 |
+
"loss": 19.7198,
|
| 798 |
+
"mean_token_accuracy": 0.685746643692255,
|
| 799 |
+
"num_tokens": 2804340.0,
|
| 800 |
+
"step": 570
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 1.2075012478977443,
|
| 804 |
+
"epoch": 0.232,
|
| 805 |
+
"grad_norm": 80.0,
|
| 806 |
+
"learning_rate": 1.9005555555555557e-05,
|
| 807 |
+
"loss": 19.6344,
|
| 808 |
+
"mean_token_accuracy": 0.6857940997928381,
|
| 809 |
+
"num_tokens": 2852298.0,
|
| 810 |
+
"step": 580
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 1.1989578040316702,
|
| 814 |
+
"epoch": 0.236,
|
| 815 |
+
"grad_norm": 85.5,
|
| 816 |
+
"learning_rate": 1.8950000000000003e-05,
|
| 817 |
+
"loss": 19.3132,
|
| 818 |
+
"mean_token_accuracy": 0.6939592262730002,
|
| 819 |
+
"num_tokens": 2901227.0,
|
| 820 |
+
"step": 590
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 1.2394503276795148,
|
| 824 |
+
"epoch": 0.24,
|
| 825 |
+
"grad_norm": 99.5,
|
| 826 |
+
"learning_rate": 1.8894444444444446e-05,
|
| 827 |
+
"loss": 20.0171,
|
| 828 |
+
"mean_token_accuracy": 0.6842290829867125,
|
| 829 |
+
"num_tokens": 2947346.0,
|
| 830 |
+
"step": 600
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.24,
|
| 834 |
+
"eval_biology_entropy": 1.1514823293685914,
|
| 835 |
+
"eval_biology_loss": 1.2215782403945923,
|
| 836 |
+
"eval_biology_mean_token_accuracy": 0.6902710503339767,
|
| 837 |
+
"eval_biology_num_tokens": 2947346.0,
|
| 838 |
+
"eval_biology_runtime": 36.8865,
|
| 839 |
+
"eval_biology_samples_per_second": 13.555,
|
| 840 |
+
"eval_biology_steps_per_second": 13.555,
|
| 841 |
+
"step": 600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.24,
|
| 845 |
+
"eval_chemistry_entropy": 0.8571230885386467,
|
| 846 |
+
"eval_chemistry_loss": 0.9023940563201904,
|
| 847 |
+
"eval_chemistry_mean_token_accuracy": 0.7593449745774269,
|
| 848 |
+
"eval_chemistry_num_tokens": 2947346.0,
|
| 849 |
+
"eval_chemistry_runtime": 40.0868,
|
| 850 |
+
"eval_chemistry_samples_per_second": 12.473,
|
| 851 |
+
"eval_chemistry_steps_per_second": 12.473,
|
| 852 |
+
"step": 600
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.24,
|
| 856 |
+
"eval_math_entropy": 0.7442211763560772,
|
| 857 |
+
"eval_math_loss": 0.9054449200630188,
|
| 858 |
+
"eval_math_mean_token_accuracy": 0.76559605550766,
|
| 859 |
+
"eval_math_num_tokens": 2947346.0,
|
| 860 |
+
"eval_math_runtime": 41.6093,
|
| 861 |
+
"eval_math_samples_per_second": 12.017,
|
| 862 |
+
"eval_math_steps_per_second": 12.017,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.24,
|
| 867 |
+
"eval_physics_entropy": 0.7813739073872566,
|
| 868 |
+
"eval_physics_loss": 0.8251622319221497,
|
| 869 |
+
"eval_physics_mean_token_accuracy": 0.7764079115390777,
|
| 870 |
+
"eval_physics_num_tokens": 2947346.0,
|
| 871 |
+
"eval_physics_runtime": 45.5977,
|
| 872 |
+
"eval_physics_samples_per_second": 10.965,
|
| 873 |
+
"eval_physics_steps_per_second": 10.965,
|
| 874 |
+
"step": 600
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"entropy": 1.2816234160214663,
|
| 878 |
+
"epoch": 0.244,
|
| 879 |
+
"grad_norm": 82.0,
|
| 880 |
+
"learning_rate": 1.883888888888889e-05,
|
| 881 |
+
"loss": 20.3578,
|
| 882 |
+
"mean_token_accuracy": 0.6772410158067942,
|
| 883 |
+
"num_tokens": 2996175.0,
|
| 884 |
+
"step": 610
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"entropy": 1.2542358499020339,
|
| 888 |
+
"epoch": 0.248,
|
| 889 |
+
"grad_norm": 77.0,
|
| 890 |
+
"learning_rate": 1.8783333333333337e-05,
|
| 891 |
+
"loss": 20.4992,
|
| 892 |
+
"mean_token_accuracy": 0.6766950022429228,
|
| 893 |
+
"num_tokens": 3043128.0,
|
| 894 |
+
"step": 620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"entropy": 1.2298073736950754,
|
| 898 |
+
"epoch": 0.252,
|
| 899 |
+
"grad_norm": 76.0,
|
| 900 |
+
"learning_rate": 1.872777777777778e-05,
|
| 901 |
+
"loss": 19.7128,
|
| 902 |
+
"mean_token_accuracy": 0.6849291998893022,
|
| 903 |
+
"num_tokens": 3090827.0,
|
| 904 |
+
"step": 630
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"entropy": 1.1652949508279562,
|
| 908 |
+
"epoch": 0.256,
|
| 909 |
+
"grad_norm": 87.0,
|
| 910 |
+
"learning_rate": 1.8672222222222222e-05,
|
| 911 |
+
"loss": 19.0561,
|
| 912 |
+
"mean_token_accuracy": 0.6929412636905908,
|
| 913 |
+
"num_tokens": 3139957.0,
|
| 914 |
+
"step": 640
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"entropy": 1.2646588858217,
|
| 918 |
+
"epoch": 0.26,
|
| 919 |
+
"grad_norm": 84.0,
|
| 920 |
+
"learning_rate": 1.8616666666666667e-05,
|
| 921 |
+
"loss": 20.0112,
|
| 922 |
+
"mean_token_accuracy": 0.6835361944511533,
|
| 923 |
+
"num_tokens": 3183188.0,
|
| 924 |
+
"step": 650
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"entropy": 1.2171090628951788,
|
| 928 |
+
"epoch": 0.264,
|
| 929 |
+
"grad_norm": 81.5,
|
| 930 |
+
"learning_rate": 1.8561111111111113e-05,
|
| 931 |
+
"loss": 19.9192,
|
| 932 |
+
"mean_token_accuracy": 0.6854063520208001,
|
| 933 |
+
"num_tokens": 3232159.0,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"entropy": 1.218252230808139,
|
| 938 |
+
"epoch": 0.268,
|
| 939 |
+
"grad_norm": 76.5,
|
| 940 |
+
"learning_rate": 1.8505555555555556e-05,
|
| 941 |
+
"loss": 19.4163,
|
| 942 |
+
"mean_token_accuracy": 0.6893998075276613,
|
| 943 |
+
"num_tokens": 3283908.0,
|
| 944 |
+
"step": 670
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"entropy": 1.1729648176580667,
|
| 948 |
+
"epoch": 0.272,
|
| 949 |
+
"grad_norm": 101.0,
|
| 950 |
+
"learning_rate": 1.845e-05,
|
| 951 |
+
"loss": 19.422,
|
| 952 |
+
"mean_token_accuracy": 0.6887724719941616,
|
| 953 |
+
"num_tokens": 3335951.0,
|
| 954 |
+
"step": 680
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"entropy": 1.2519408775493504,
|
| 958 |
+
"epoch": 0.276,
|
| 959 |
+
"grad_norm": 90.5,
|
| 960 |
+
"learning_rate": 1.8394444444444447e-05,
|
| 961 |
+
"loss": 19.8039,
|
| 962 |
+
"mean_token_accuracy": 0.6823019618168473,
|
| 963 |
+
"num_tokens": 3387755.0,
|
| 964 |
+
"step": 690
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"entropy": 1.195892432704568,
|
| 968 |
+
"epoch": 0.28,
|
| 969 |
+
"grad_norm": 84.0,
|
| 970 |
+
"learning_rate": 1.833888888888889e-05,
|
| 971 |
+
"loss": 19.5225,
|
| 972 |
+
"mean_token_accuracy": 0.685329046845436,
|
| 973 |
+
"num_tokens": 3437213.0,
|
| 974 |
+
"step": 700
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.28,
|
| 978 |
+
"eval_biology_entropy": 1.2085156010985374,
|
| 979 |
+
"eval_biology_loss": 1.207029104232788,
|
| 980 |
+
"eval_biology_mean_token_accuracy": 0.6939799420833588,
|
| 981 |
+
"eval_biology_num_tokens": 3437213.0,
|
| 982 |
+
"eval_biology_runtime": 36.7099,
|
| 983 |
+
"eval_biology_samples_per_second": 13.62,
|
| 984 |
+
"eval_biology_steps_per_second": 13.62,
|
| 985 |
+
"step": 700
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.28,
|
| 989 |
+
"eval_chemistry_entropy": 0.9005156295895577,
|
| 990 |
+
"eval_chemistry_loss": 0.9021785855293274,
|
| 991 |
+
"eval_chemistry_mean_token_accuracy": 0.7585515556931496,
|
| 992 |
+
"eval_chemistry_num_tokens": 3437213.0,
|
| 993 |
+
"eval_chemistry_runtime": 40.2932,
|
| 994 |
+
"eval_chemistry_samples_per_second": 12.409,
|
| 995 |
+
"eval_chemistry_steps_per_second": 12.409,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.28,
|
| 1000 |
+
"eval_math_entropy": 0.7635650929510593,
|
| 1001 |
+
"eval_math_loss": 0.9004127979278564,
|
| 1002 |
+
"eval_math_mean_token_accuracy": 0.7664950026273727,
|
| 1003 |
+
"eval_math_num_tokens": 3437213.0,
|
| 1004 |
+
"eval_math_runtime": 40.3086,
|
| 1005 |
+
"eval_math_samples_per_second": 12.404,
|
| 1006 |
+
"eval_math_steps_per_second": 12.404,
|
| 1007 |
+
"step": 700
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.28,
|
| 1011 |
+
"eval_physics_entropy": 0.8227353655099868,
|
| 1012 |
+
"eval_physics_loss": 0.8242940902709961,
|
| 1013 |
+
"eval_physics_mean_token_accuracy": 0.7775262135863305,
|
| 1014 |
+
"eval_physics_num_tokens": 3437213.0,
|
| 1015 |
+
"eval_physics_runtime": 44.9118,
|
| 1016 |
+
"eval_physics_samples_per_second": 11.133,
|
| 1017 |
+
"eval_physics_steps_per_second": 11.133,
|
| 1018 |
+
"step": 700
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"entropy": 1.1728057231754065,
|
| 1022 |
+
"epoch": 0.284,
|
| 1023 |
+
"grad_norm": 67.5,
|
| 1024 |
+
"learning_rate": 1.8283333333333335e-05,
|
| 1025 |
+
"loss": 18.654,
|
| 1026 |
+
"mean_token_accuracy": 0.6981678586453199,
|
| 1027 |
+
"num_tokens": 3489088.0,
|
| 1028 |
+
"step": 710
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"entropy": 1.1936262086033822,
|
| 1032 |
+
"epoch": 0.288,
|
| 1033 |
+
"grad_norm": 72.5,
|
| 1034 |
+
"learning_rate": 1.822777777777778e-05,
|
| 1035 |
+
"loss": 19.517,
|
| 1036 |
+
"mean_token_accuracy": 0.6882296811789275,
|
| 1037 |
+
"num_tokens": 3539731.0,
|
| 1038 |
+
"step": 720
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"entropy": 1.2277162373065948,
|
| 1042 |
+
"epoch": 0.292,
|
| 1043 |
+
"grad_norm": 75.5,
|
| 1044 |
+
"learning_rate": 1.8172222222222223e-05,
|
| 1045 |
+
"loss": 19.4898,
|
| 1046 |
+
"mean_token_accuracy": 0.6886593095958233,
|
| 1047 |
+
"num_tokens": 3586433.0,
|
| 1048 |
+
"step": 730
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"entropy": 1.2317656818777323,
|
| 1052 |
+
"epoch": 0.296,
|
| 1053 |
+
"grad_norm": 79.0,
|
| 1054 |
+
"learning_rate": 1.811666666666667e-05,
|
| 1055 |
+
"loss": 20.2521,
|
| 1056 |
+
"mean_token_accuracy": 0.6818229380995036,
|
| 1057 |
+
"num_tokens": 3633448.0,
|
| 1058 |
+
"step": 740
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"entropy": 1.1757729103788734,
|
| 1062 |
+
"epoch": 0.3,
|
| 1063 |
+
"grad_norm": 75.0,
|
| 1064 |
+
"learning_rate": 1.806111111111111e-05,
|
| 1065 |
+
"loss": 18.6931,
|
| 1066 |
+
"mean_token_accuracy": 0.701389448530972,
|
| 1067 |
+
"num_tokens": 3685080.0,
|
| 1068 |
+
"step": 750
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"entropy": 1.1586591433733702,
|
| 1072 |
+
"epoch": 0.304,
|
| 1073 |
+
"grad_norm": 77.5,
|
| 1074 |
+
"learning_rate": 1.8005555555555557e-05,
|
| 1075 |
+
"loss": 18.9227,
|
| 1076 |
+
"mean_token_accuracy": 0.69391386564821,
|
| 1077 |
+
"num_tokens": 3733488.0,
|
| 1078 |
+
"step": 760
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"entropy": 1.2230437025427818,
|
| 1082 |
+
"epoch": 0.308,
|
| 1083 |
+
"grad_norm": 76.0,
|
| 1084 |
+
"learning_rate": 1.795e-05,
|
| 1085 |
+
"loss": 19.675,
|
| 1086 |
+
"mean_token_accuracy": 0.6864967104047537,
|
| 1087 |
+
"num_tokens": 3779708.0,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"entropy": 1.21304402500391,
|
| 1092 |
+
"epoch": 0.312,
|
| 1093 |
+
"grad_norm": 85.0,
|
| 1094 |
+
"learning_rate": 1.7894444444444445e-05,
|
| 1095 |
+
"loss": 19.5388,
|
| 1096 |
+
"mean_token_accuracy": 0.6890883000567556,
|
| 1097 |
+
"num_tokens": 3825212.0,
|
| 1098 |
+
"step": 780
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"entropy": 1.2525564279407262,
|
| 1102 |
+
"epoch": 0.316,
|
| 1103 |
+
"grad_norm": 89.5,
|
| 1104 |
+
"learning_rate": 1.783888888888889e-05,
|
| 1105 |
+
"loss": 20.2117,
|
| 1106 |
+
"mean_token_accuracy": 0.6794506318867206,
|
| 1107 |
+
"num_tokens": 3870912.0,
|
| 1108 |
+
"step": 790
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"entropy": 1.2013506395742297,
|
| 1112 |
+
"epoch": 0.32,
|
| 1113 |
+
"grad_norm": 88.5,
|
| 1114 |
+
"learning_rate": 1.7783333333333333e-05,
|
| 1115 |
+
"loss": 19.2548,
|
| 1116 |
+
"mean_token_accuracy": 0.6915859717875719,
|
| 1117 |
+
"num_tokens": 3920545.0,
|
| 1118 |
+
"step": 800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.32,
|
| 1122 |
+
"eval_biology_entropy": 1.1828332220315934,
|
| 1123 |
+
"eval_biology_loss": 1.1939783096313477,
|
| 1124 |
+
"eval_biology_mean_token_accuracy": 0.6965516614317894,
|
| 1125 |
+
"eval_biology_num_tokens": 3920545.0,
|
| 1126 |
+
"eval_biology_runtime": 35.8369,
|
| 1127 |
+
"eval_biology_samples_per_second": 13.952,
|
| 1128 |
+
"eval_biology_steps_per_second": 13.952,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.32,
|
| 1133 |
+
"eval_chemistry_entropy": 0.886673482120037,
|
| 1134 |
+
"eval_chemistry_loss": 0.8999966979026794,
|
| 1135 |
+
"eval_chemistry_mean_token_accuracy": 0.7598078215122223,
|
| 1136 |
+
"eval_chemistry_num_tokens": 3920545.0,
|
| 1137 |
+
"eval_chemistry_runtime": 40.2857,
|
| 1138 |
+
"eval_chemistry_samples_per_second": 12.411,
|
| 1139 |
+
"eval_chemistry_steps_per_second": 12.411,
|
| 1140 |
+
"step": 800
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.32,
|
| 1144 |
+
"eval_math_entropy": 0.7587899960577488,
|
| 1145 |
+
"eval_math_loss": 0.8991398215293884,
|
| 1146 |
+
"eval_math_mean_token_accuracy": 0.7670052968263626,
|
| 1147 |
+
"eval_math_num_tokens": 3920545.0,
|
| 1148 |
+
"eval_math_runtime": 41.3295,
|
| 1149 |
+
"eval_math_samples_per_second": 12.098,
|
| 1150 |
+
"eval_math_steps_per_second": 12.098,
|
| 1151 |
+
"step": 800
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.32,
|
| 1155 |
+
"eval_physics_entropy": 0.8086917443871499,
|
| 1156 |
+
"eval_physics_loss": 0.820421576499939,
|
| 1157 |
+
"eval_physics_mean_token_accuracy": 0.7782125360369683,
|
| 1158 |
+
"eval_physics_num_tokens": 3920545.0,
|
| 1159 |
+
"eval_physics_runtime": 45.2584,
|
| 1160 |
+
"eval_physics_samples_per_second": 11.048,
|
| 1161 |
+
"eval_physics_steps_per_second": 11.048,
|
| 1162 |
+
"step": 800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"entropy": 1.2068503752350808,
|
| 1166 |
+
"epoch": 0.324,
|
| 1167 |
+
"grad_norm": 79.5,
|
| 1168 |
+
"learning_rate": 1.772777777777778e-05,
|
| 1169 |
+
"loss": 19.4093,
|
| 1170 |
+
"mean_token_accuracy": 0.6900258323177695,
|
| 1171 |
+
"num_tokens": 3967499.0,
|
| 1172 |
+
"step": 810
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"entropy": 1.1701661001890897,
|
| 1176 |
+
"epoch": 0.328,
|
| 1177 |
+
"grad_norm": 72.5,
|
| 1178 |
+
"learning_rate": 1.7672222222222224e-05,
|
| 1179 |
+
"loss": 18.743,
|
| 1180 |
+
"mean_token_accuracy": 0.6989876503124833,
|
| 1181 |
+
"num_tokens": 4016673.0,
|
| 1182 |
+
"step": 820
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"entropy": 1.2040905393660069,
|
| 1186 |
+
"epoch": 0.332,
|
| 1187 |
+
"grad_norm": 80.0,
|
| 1188 |
+
"learning_rate": 1.761666666666667e-05,
|
| 1189 |
+
"loss": 19.7643,
|
| 1190 |
+
"mean_token_accuracy": 0.6862274307757616,
|
| 1191 |
+
"num_tokens": 4063859.0,
|
| 1192 |
+
"step": 830
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"entropy": 1.1994104048237204,
|
| 1196 |
+
"epoch": 0.336,
|
| 1197 |
+
"grad_norm": 75.5,
|
| 1198 |
+
"learning_rate": 1.7561111111111113e-05,
|
| 1199 |
+
"loss": 19.1933,
|
| 1200 |
+
"mean_token_accuracy": 0.6893992654979229,
|
| 1201 |
+
"num_tokens": 4114077.0,
|
| 1202 |
+
"step": 840
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"entropy": 1.21622231900692,
|
| 1206 |
+
"epoch": 0.34,
|
| 1207 |
+
"grad_norm": 75.5,
|
| 1208 |
+
"learning_rate": 1.7505555555555558e-05,
|
| 1209 |
+
"loss": 19.6288,
|
| 1210 |
+
"mean_token_accuracy": 0.6871093420311809,
|
| 1211 |
+
"num_tokens": 4160168.0,
|
| 1212 |
+
"step": 850
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"entropy": 1.1868847006931902,
|
| 1216 |
+
"epoch": 0.344,
|
| 1217 |
+
"grad_norm": 72.5,
|
| 1218 |
+
"learning_rate": 1.7450000000000004e-05,
|
| 1219 |
+
"loss": 19.3293,
|
| 1220 |
+
"mean_token_accuracy": 0.6937917049974203,
|
| 1221 |
+
"num_tokens": 4210403.0,
|
| 1222 |
+
"step": 860
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"entropy": 1.1898768026381732,
|
| 1226 |
+
"epoch": 0.348,
|
| 1227 |
+
"grad_norm": 74.5,
|
| 1228 |
+
"learning_rate": 1.7394444444444446e-05,
|
| 1229 |
+
"loss": 18.7152,
|
| 1230 |
+
"mean_token_accuracy": 0.6979909218847752,
|
| 1231 |
+
"num_tokens": 4256944.0,
|
| 1232 |
+
"step": 870
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"entropy": 1.1888672057539225,
|
| 1236 |
+
"epoch": 0.352,
|
| 1237 |
+
"grad_norm": 75.5,
|
| 1238 |
+
"learning_rate": 1.733888888888889e-05,
|
| 1239 |
+
"loss": 19.4446,
|
| 1240 |
+
"mean_token_accuracy": 0.6919016648083925,
|
| 1241 |
+
"num_tokens": 4306949.0,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"entropy": 1.1983365084975959,
|
| 1246 |
+
"epoch": 0.356,
|
| 1247 |
+
"grad_norm": 69.0,
|
| 1248 |
+
"learning_rate": 1.7283333333333334e-05,
|
| 1249 |
+
"loss": 19.2777,
|
| 1250 |
+
"mean_token_accuracy": 0.6915557283908129,
|
| 1251 |
+
"num_tokens": 4355070.0,
|
| 1252 |
+
"step": 890
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"entropy": 1.1921971619129181,
|
| 1256 |
+
"epoch": 0.36,
|
| 1257 |
+
"grad_norm": 63.75,
|
| 1258 |
+
"learning_rate": 1.722777777777778e-05,
|
| 1259 |
+
"loss": 19.2026,
|
| 1260 |
+
"mean_token_accuracy": 0.6915637668222189,
|
| 1261 |
+
"num_tokens": 4406104.0,
|
| 1262 |
+
"step": 900
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.36,
|
| 1266 |
+
"eval_biology_entropy": 1.1541215604543686,
|
| 1267 |
+
"eval_biology_loss": 1.1821783781051636,
|
| 1268 |
+
"eval_biology_mean_token_accuracy": 0.6984301459789276,
|
| 1269 |
+
"eval_biology_num_tokens": 4406104.0,
|
| 1270 |
+
"eval_biology_runtime": 35.8688,
|
| 1271 |
+
"eval_biology_samples_per_second": 13.94,
|
| 1272 |
+
"eval_biology_steps_per_second": 13.94,
|
| 1273 |
+
"step": 900
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.36,
|
| 1277 |
+
"eval_chemistry_entropy": 0.8648406760692596,
|
| 1278 |
+
"eval_chemistry_loss": 0.9016790390014648,
|
| 1279 |
+
"eval_chemistry_mean_token_accuracy": 0.7602673851847649,
|
| 1280 |
+
"eval_chemistry_num_tokens": 4406104.0,
|
| 1281 |
+
"eval_chemistry_runtime": 40.1126,
|
| 1282 |
+
"eval_chemistry_samples_per_second": 12.465,
|
| 1283 |
+
"eval_chemistry_steps_per_second": 12.465,
|
| 1284 |
+
"step": 900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.36,
|
| 1288 |
+
"eval_math_entropy": 0.7475603276491165,
|
| 1289 |
+
"eval_math_loss": 0.9146779775619507,
|
| 1290 |
+
"eval_math_mean_token_accuracy": 0.7653868557214737,
|
| 1291 |
+
"eval_math_num_tokens": 4406104.0,
|
| 1292 |
+
"eval_math_runtime": 41.1141,
|
| 1293 |
+
"eval_math_samples_per_second": 12.161,
|
| 1294 |
+
"eval_math_steps_per_second": 12.161,
|
| 1295 |
+
"step": 900
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 0.36,
|
| 1299 |
+
"eval_physics_entropy": 0.782447283744812,
|
| 1300 |
+
"eval_physics_loss": 0.8322422504425049,
|
| 1301 |
+
"eval_physics_mean_token_accuracy": 0.7780593295693398,
|
| 1302 |
+
"eval_physics_num_tokens": 4406104.0,
|
| 1303 |
+
"eval_physics_runtime": 45.2444,
|
| 1304 |
+
"eval_physics_samples_per_second": 11.051,
|
| 1305 |
+
"eval_physics_steps_per_second": 11.051,
|
| 1306 |
+
"step": 900
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"entropy": 1.2114545024931431,
|
| 1310 |
+
"epoch": 0.364,
|
| 1311 |
+
"grad_norm": 73.0,
|
| 1312 |
+
"learning_rate": 1.7172222222222223e-05,
|
| 1313 |
+
"loss": 19.4011,
|
| 1314 |
+
"mean_token_accuracy": 0.6914434898644686,
|
| 1315 |
+
"num_tokens": 4455015.0,
|
| 1316 |
+
"step": 910
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"entropy": 1.1504958260804414,
|
| 1320 |
+
"epoch": 0.368,
|
| 1321 |
+
"grad_norm": 84.5,
|
| 1322 |
+
"learning_rate": 1.7116666666666668e-05,
|
| 1323 |
+
"loss": 18.8783,
|
| 1324 |
+
"mean_token_accuracy": 0.6960504239425063,
|
| 1325 |
+
"num_tokens": 4504001.0,
|
| 1326 |
+
"step": 920
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"entropy": 1.2334423441439868,
|
| 1330 |
+
"epoch": 0.372,
|
| 1331 |
+
"grad_norm": 76.5,
|
| 1332 |
+
"learning_rate": 1.7061111111111114e-05,
|
| 1333 |
+
"loss": 19.3716,
|
| 1334 |
+
"mean_token_accuracy": 0.6921723924577237,
|
| 1335 |
+
"num_tokens": 4550269.0,
|
| 1336 |
+
"step": 930
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"entropy": 1.138117073662579,
|
| 1340 |
+
"epoch": 0.376,
|
| 1341 |
+
"grad_norm": 81.0,
|
| 1342 |
+
"learning_rate": 1.7005555555555556e-05,
|
| 1343 |
+
"loss": 18.6873,
|
| 1344 |
+
"mean_token_accuracy": 0.6977444339543581,
|
| 1345 |
+
"num_tokens": 4597559.0,
|
| 1346 |
+
"step": 940
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"entropy": 1.1804296549409627,
|
| 1350 |
+
"epoch": 0.38,
|
| 1351 |
+
"grad_norm": 84.5,
|
| 1352 |
+
"learning_rate": 1.6950000000000002e-05,
|
| 1353 |
+
"loss": 18.7748,
|
| 1354 |
+
"mean_token_accuracy": 0.6972912590950727,
|
| 1355 |
+
"num_tokens": 4646903.0,
|
| 1356 |
+
"step": 950
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"entropy": 1.1713591821491718,
|
| 1360 |
+
"epoch": 0.384,
|
| 1361 |
+
"grad_norm": 71.5,
|
| 1362 |
+
"learning_rate": 1.6894444444444448e-05,
|
| 1363 |
+
"loss": 19.1636,
|
| 1364 |
+
"mean_token_accuracy": 0.6900384306907654,
|
| 1365 |
+
"num_tokens": 4693812.0,
|
| 1366 |
+
"step": 960
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"entropy": 1.20406583994627,
|
| 1370 |
+
"epoch": 0.388,
|
| 1371 |
+
"grad_norm": 75.0,
|
| 1372 |
+
"learning_rate": 1.683888888888889e-05,
|
| 1373 |
+
"loss": 19.1408,
|
| 1374 |
+
"mean_token_accuracy": 0.6931487508118153,
|
| 1375 |
+
"num_tokens": 4740309.0,
|
| 1376 |
+
"step": 970
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"entropy": 1.2038170533254742,
|
| 1380 |
+
"epoch": 0.392,
|
| 1381 |
+
"grad_norm": 71.5,
|
| 1382 |
+
"learning_rate": 1.6783333333333332e-05,
|
| 1383 |
+
"loss": 19.1738,
|
| 1384 |
+
"mean_token_accuracy": 0.6930541478097438,
|
| 1385 |
+
"num_tokens": 4790965.0,
|
| 1386 |
+
"step": 980
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"entropy": 1.1741992883384227,
|
| 1390 |
+
"epoch": 0.396,
|
| 1391 |
+
"grad_norm": 76.0,
|
| 1392 |
+
"learning_rate": 1.6727777777777778e-05,
|
| 1393 |
+
"loss": 19.1958,
|
| 1394 |
+
"mean_token_accuracy": 0.6922040678560734,
|
| 1395 |
+
"num_tokens": 4839186.0,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"entropy": 1.2012158632278442,
|
| 1400 |
+
"epoch": 0.4,
|
| 1401 |
+
"grad_norm": 77.5,
|
| 1402 |
+
"learning_rate": 1.6672222222222224e-05,
|
| 1403 |
+
"loss": 19.1545,
|
| 1404 |
+
"mean_token_accuracy": 0.6926527272909879,
|
| 1405 |
+
"num_tokens": 4887094.0,
|
| 1406 |
+
"step": 1000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.4,
|
| 1410 |
+
"eval_biology_entropy": 1.153373451292515,
|
| 1411 |
+
"eval_biology_loss": 1.1686452627182007,
|
| 1412 |
+
"eval_biology_mean_token_accuracy": 0.7013231556415558,
|
| 1413 |
+
"eval_biology_num_tokens": 4887094.0,
|
| 1414 |
+
"eval_biology_runtime": 36.1843,
|
| 1415 |
+
"eval_biology_samples_per_second": 13.818,
|
| 1416 |
+
"eval_biology_steps_per_second": 13.818,
|
| 1417 |
+
"step": 1000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.4,
|
| 1421 |
+
"eval_chemistry_entropy": 0.8627612872719764,
|
| 1422 |
+
"eval_chemistry_loss": 0.8771724104881287,
|
| 1423 |
+
"eval_chemistry_mean_token_accuracy": 0.7635843125581742,
|
| 1424 |
+
"eval_chemistry_num_tokens": 4887094.0,
|
| 1425 |
+
"eval_chemistry_runtime": 39.65,
|
| 1426 |
+
"eval_chemistry_samples_per_second": 12.61,
|
| 1427 |
+
"eval_chemistry_steps_per_second": 12.61,
|
| 1428 |
+
"step": 1000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.4,
|
| 1432 |
+
"eval_math_entropy": 0.7435729750990867,
|
| 1433 |
+
"eval_math_loss": 0.8909226655960083,
|
| 1434 |
+
"eval_math_mean_token_accuracy": 0.7684622532129288,
|
| 1435 |
+
"eval_math_num_tokens": 4887094.0,
|
| 1436 |
+
"eval_math_runtime": 40.3632,
|
| 1437 |
+
"eval_math_samples_per_second": 12.388,
|
| 1438 |
+
"eval_math_steps_per_second": 12.388,
|
| 1439 |
+
"step": 1000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.4,
|
| 1443 |
+
"eval_physics_entropy": 0.7918061959147453,
|
| 1444 |
+
"eval_physics_loss": 0.8059831261634827,
|
| 1445 |
+
"eval_physics_mean_token_accuracy": 0.7804628658294678,
|
| 1446 |
+
"eval_physics_num_tokens": 4887094.0,
|
| 1447 |
+
"eval_physics_runtime": 44.9291,
|
| 1448 |
+
"eval_physics_samples_per_second": 11.129,
|
| 1449 |
+
"eval_physics_steps_per_second": 11.129,
|
| 1450 |
+
"step": 1000
|
| 1451 |
+
}
|
| 1452 |
+
],
|
| 1453 |
+
"logging_steps": 10,
|
| 1454 |
+
"max_steps": 4000,
|
| 1455 |
+
"num_input_tokens_seen": 0,
|
| 1456 |
+
"num_train_epochs": 2,
|
| 1457 |
+
"save_steps": 500,
|
| 1458 |
+
"stateful_callbacks": {
|
| 1459 |
+
"TrainerControl": {
|
| 1460 |
+
"args": {
|
| 1461 |
+
"should_epoch_stop": false,
|
| 1462 |
+
"should_evaluate": false,
|
| 1463 |
+
"should_log": false,
|
| 1464 |
+
"should_save": true,
|
| 1465 |
+
"should_training_stop": false
|
| 1466 |
+
},
|
| 1467 |
+
"attributes": {}
|
| 1468 |
+
}
|
| 1469 |
+
},
|
| 1470 |
+
"total_flos": 3.277009915508544e+17,
|
| 1471 |
+
"train_batch_size": 1,
|
| 1472 |
+
"trial_name": null,
|
| 1473 |
+
"trial_params": null
|
| 1474 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:205821b272c9e6374ffc464c4b2a6e8583b5f21d0bcc22110be9735c8da9d3f0
|
| 3 |
+
size 6481
|