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 sha256:7cee411d9d57324e50ce064a192cc5a858276d508611b12fc599e0c9767112e0
|
| 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 sha256:8bc75a29a730c9e743cad013feda3b0991a913fafe787c58a1c6e20afad97723
|
| 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:e0f205868768699a931b354b7408cae891c8539cd5ab406138a969d6a3a8d3c0
|
| 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 sha256:5a5678af941b16ffd253f75ff44646eb3b84bea99e77195e691a3d08cc3503c9
|
| 3 |
+
size 896607944
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:471b1c653aabe47d1dda07893496c6ec8f21353cd348bef0e1f9b8b6dd76552c
|
| 3 |
+
size 14645
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f23267b381a42784999e08fdda207042bbe3b9bc2b38cecbe7bd208dc572c4ab
|
| 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": 1.6,
|
| 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": 0.7081545192748309,
|
| 14 |
+
"epoch": 0.016,
|
| 15 |
+
"grad_norm": 119.5,
|
| 16 |
+
"learning_rate": 6.000000000000001e-07,
|
| 17 |
+
"loss": 30.4211,
|
| 18 |
+
"mean_token_accuracy": 0.7030085142701864,
|
| 19 |
+
"num_tokens": 338352.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.7043411549180746,
|
| 24 |
+
"epoch": 0.032,
|
| 25 |
+
"grad_norm": 111.5,
|
| 26 |
+
"learning_rate": 1.2666666666666669e-06,
|
| 27 |
+
"loss": 30.1214,
|
| 28 |
+
"mean_token_accuracy": 0.7080705553293228,
|
| 29 |
+
"num_tokens": 671193.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.7044402219355106,
|
| 34 |
+
"epoch": 0.048,
|
| 35 |
+
"grad_norm": 106.0,
|
| 36 |
+
"learning_rate": 1.9333333333333336e-06,
|
| 37 |
+
"loss": 29.7341,
|
| 38 |
+
"mean_token_accuracy": 0.7064134150743484,
|
| 39 |
+
"num_tokens": 1001008.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.733870861120522,
|
| 44 |
+
"epoch": 0.064,
|
| 45 |
+
"grad_norm": 96.0,
|
| 46 |
+
"learning_rate": 2.6e-06,
|
| 47 |
+
"loss": 30.1494,
|
| 48 |
+
"mean_token_accuracy": 0.7005880128592252,
|
| 49 |
+
"num_tokens": 1331208.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7398215295746923,
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"grad_norm": 90.5,
|
| 56 |
+
"learning_rate": 3.266666666666667e-06,
|
| 57 |
+
"loss": 28.7202,
|
| 58 |
+
"mean_token_accuracy": 0.7051243670284748,
|
| 59 |
+
"num_tokens": 1667532.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.738157893717289,
|
| 64 |
+
"epoch": 0.096,
|
| 65 |
+
"grad_norm": 76.5,
|
| 66 |
+
"learning_rate": 3.9333333333333335e-06,
|
| 67 |
+
"loss": 27.1633,
|
| 68 |
+
"mean_token_accuracy": 0.71303277797997,
|
| 69 |
+
"num_tokens": 2007176.0,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.8131938450038433,
|
| 74 |
+
"epoch": 0.112,
|
| 75 |
+
"grad_norm": 57.5,
|
| 76 |
+
"learning_rate": 4.600000000000001e-06,
|
| 77 |
+
"loss": 26.4428,
|
| 78 |
+
"mean_token_accuracy": 0.7120848346501589,
|
| 79 |
+
"num_tokens": 2342259.0,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.9618701986968518,
|
| 84 |
+
"epoch": 0.128,
|
| 85 |
+
"grad_norm": 43.75,
|
| 86 |
+
"learning_rate": 5.2666666666666665e-06,
|
| 87 |
+
"loss": 25.9908,
|
| 88 |
+
"mean_token_accuracy": 0.7077770136296749,
|
| 89 |
+
"num_tokens": 2663987.0,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.0031472396105527,
|
| 94 |
+
"epoch": 0.144,
|
| 95 |
+
"grad_norm": 30.125,
|
| 96 |
+
"learning_rate": 5.933333333333335e-06,
|
| 97 |
+
"loss": 23.3524,
|
| 98 |
+
"mean_token_accuracy": 0.7268724206835031,
|
| 99 |
+
"num_tokens": 2997824.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.0786659345030785,
|
| 104 |
+
"epoch": 0.16,
|
| 105 |
+
"grad_norm": 20.75,
|
| 106 |
+
"learning_rate": 6.600000000000001e-06,
|
| 107 |
+
"loss": 21.8746,
|
| 108 |
+
"mean_token_accuracy": 0.7358953565359115,
|
| 109 |
+
"num_tokens": 3330597.0,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.16,
|
| 114 |
+
"eval_biology_entropy": 3.260982286453247,
|
| 115 |
+
"eval_biology_loss": 3.7093346118927,
|
| 116 |
+
"eval_biology_mean_token_accuracy": 0.46263515305519104,
|
| 117 |
+
"eval_biology_num_tokens": 3330597.0,
|
| 118 |
+
"eval_biology_runtime": 57.0058,
|
| 119 |
+
"eval_biology_samples_per_second": 8.771,
|
| 120 |
+
"eval_biology_steps_per_second": 2.193,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.16,
|
| 125 |
+
"eval_chemistry_entropy": 1.6407185397148132,
|
| 126 |
+
"eval_chemistry_loss": 1.7927597761154175,
|
| 127 |
+
"eval_chemistry_mean_token_accuracy": 0.677183347940445,
|
| 128 |
+
"eval_chemistry_num_tokens": 3330597.0,
|
| 129 |
+
"eval_chemistry_runtime": 71.6705,
|
| 130 |
+
"eval_chemistry_samples_per_second": 6.976,
|
| 131 |
+
"eval_chemistry_steps_per_second": 1.744,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.16,
|
| 136 |
+
"eval_math_entropy": 0.9620108480453491,
|
| 137 |
+
"eval_math_loss": 1.4342334270477295,
|
| 138 |
+
"eval_math_mean_token_accuracy": 0.7288489332199096,
|
| 139 |
+
"eval_math_num_tokens": 3330597.0,
|
| 140 |
+
"eval_math_runtime": 74.2141,
|
| 141 |
+
"eval_math_samples_per_second": 6.737,
|
| 142 |
+
"eval_math_steps_per_second": 1.684,
|
| 143 |
+
"step": 100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.16,
|
| 147 |
+
"eval_physics_entropy": 1.1280243759155273,
|
| 148 |
+
"eval_physics_loss": 1.3446351289749146,
|
| 149 |
+
"eval_physics_mean_token_accuracy": 0.7332401766777038,
|
| 150 |
+
"eval_physics_num_tokens": 3330597.0,
|
| 151 |
+
"eval_physics_runtime": 84.9827,
|
| 152 |
+
"eval_physics_samples_per_second": 5.884,
|
| 153 |
+
"eval_physics_steps_per_second": 1.471,
|
| 154 |
+
"step": 100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"entropy": 1.1533773414790631,
|
| 158 |
+
"epoch": 0.176,
|
| 159 |
+
"grad_norm": 19.75,
|
| 160 |
+
"learning_rate": 7.266666666666668e-06,
|
| 161 |
+
"loss": 21.3285,
|
| 162 |
+
"mean_token_accuracy": 0.7356826655566693,
|
| 163 |
+
"num_tokens": 3658264.0,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"entropy": 1.112282781302929,
|
| 168 |
+
"epoch": 0.192,
|
| 169 |
+
"grad_norm": 12.625,
|
| 170 |
+
"learning_rate": 7.933333333333334e-06,
|
| 171 |
+
"loss": 20.4084,
|
| 172 |
+
"mean_token_accuracy": 0.7426700782030821,
|
| 173 |
+
"num_tokens": 3995568.0,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"entropy": 1.086438114568591,
|
| 178 |
+
"epoch": 0.208,
|
| 179 |
+
"grad_norm": 13.875,
|
| 180 |
+
"learning_rate": 8.6e-06,
|
| 181 |
+
"loss": 19.3962,
|
| 182 |
+
"mean_token_accuracy": 0.7525120593607426,
|
| 183 |
+
"num_tokens": 4321436.0,
|
| 184 |
+
"step": 130
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"entropy": 1.089601282030344,
|
| 188 |
+
"epoch": 0.224,
|
| 189 |
+
"grad_norm": 11.8125,
|
| 190 |
+
"learning_rate": 9.266666666666667e-06,
|
| 191 |
+
"loss": 19.0472,
|
| 192 |
+
"mean_token_accuracy": 0.7530231148004531,
|
| 193 |
+
"num_tokens": 4648491.0,
|
| 194 |
+
"step": 140
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"entropy": 1.0804125092923642,
|
| 198 |
+
"epoch": 0.24,
|
| 199 |
+
"grad_norm": 11.8125,
|
| 200 |
+
"learning_rate": 9.933333333333334e-06,
|
| 201 |
+
"loss": 18.7739,
|
| 202 |
+
"mean_token_accuracy": 0.7554640270769596,
|
| 203 |
+
"num_tokens": 4986175.0,
|
| 204 |
+
"step": 150
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"entropy": 1.0836318269371987,
|
| 208 |
+
"epoch": 0.256,
|
| 209 |
+
"grad_norm": 11.9375,
|
| 210 |
+
"learning_rate": 1.0600000000000002e-05,
|
| 211 |
+
"loss": 18.4704,
|
| 212 |
+
"mean_token_accuracy": 0.7584241010248661,
|
| 213 |
+
"num_tokens": 5329320.0,
|
| 214 |
+
"step": 160
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"entropy": 1.0882270745933056,
|
| 218 |
+
"epoch": 0.272,
|
| 219 |
+
"grad_norm": 13.375,
|
| 220 |
+
"learning_rate": 1.1266666666666668e-05,
|
| 221 |
+
"loss": 18.6237,
|
| 222 |
+
"mean_token_accuracy": 0.754904105886817,
|
| 223 |
+
"num_tokens": 5658796.0,
|
| 224 |
+
"step": 170
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"entropy": 1.076054659858346,
|
| 228 |
+
"epoch": 0.288,
|
| 229 |
+
"grad_norm": 11.0625,
|
| 230 |
+
"learning_rate": 1.1933333333333335e-05,
|
| 231 |
+
"loss": 18.4139,
|
| 232 |
+
"mean_token_accuracy": 0.7581049785017967,
|
| 233 |
+
"num_tokens": 5980201.0,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"entropy": 1.072243456915021,
|
| 238 |
+
"epoch": 0.304,
|
| 239 |
+
"grad_norm": 15.5,
|
| 240 |
+
"learning_rate": 1.2600000000000001e-05,
|
| 241 |
+
"loss": 18.1532,
|
| 242 |
+
"mean_token_accuracy": 0.7589787419885397,
|
| 243 |
+
"num_tokens": 6298858.0,
|
| 244 |
+
"step": 190
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"entropy": 1.0509168311953545,
|
| 248 |
+
"epoch": 0.32,
|
| 249 |
+
"grad_norm": 12.0,
|
| 250 |
+
"learning_rate": 1.3266666666666668e-05,
|
| 251 |
+
"loss": 17.8979,
|
| 252 |
+
"mean_token_accuracy": 0.7612847778946161,
|
| 253 |
+
"num_tokens": 6622798.0,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.32,
|
| 258 |
+
"eval_biology_entropy": 2.7866374349594114,
|
| 259 |
+
"eval_biology_loss": 3.2049155235290527,
|
| 260 |
+
"eval_biology_mean_token_accuracy": 0.502942953824997,
|
| 261 |
+
"eval_biology_num_tokens": 6622798.0,
|
| 262 |
+
"eval_biology_runtime": 56.7587,
|
| 263 |
+
"eval_biology_samples_per_second": 8.809,
|
| 264 |
+
"eval_biology_steps_per_second": 2.202,
|
| 265 |
+
"step": 200
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.32,
|
| 269 |
+
"eval_chemistry_entropy": 1.41602649641037,
|
| 270 |
+
"eval_chemistry_loss": 1.4916778802871704,
|
| 271 |
+
"eval_chemistry_mean_token_accuracy": 0.7079435839653015,
|
| 272 |
+
"eval_chemistry_num_tokens": 6622798.0,
|
| 273 |
+
"eval_chemistry_runtime": 71.0228,
|
| 274 |
+
"eval_chemistry_samples_per_second": 7.04,
|
| 275 |
+
"eval_chemistry_steps_per_second": 1.76,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.32,
|
| 280 |
+
"eval_math_entropy": 0.9821910600662231,
|
| 281 |
+
"eval_math_loss": 1.256189227104187,
|
| 282 |
+
"eval_math_mean_token_accuracy": 0.7425830450057983,
|
| 283 |
+
"eval_math_num_tokens": 6622798.0,
|
| 284 |
+
"eval_math_runtime": 75.4477,
|
| 285 |
+
"eval_math_samples_per_second": 6.627,
|
| 286 |
+
"eval_math_steps_per_second": 1.657,
|
| 287 |
+
"step": 200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.32,
|
| 291 |
+
"eval_physics_entropy": 1.0466554942131043,
|
| 292 |
+
"eval_physics_loss": 1.1129223108291626,
|
| 293 |
+
"eval_physics_mean_token_accuracy": 0.7617223796844482,
|
| 294 |
+
"eval_physics_num_tokens": 6622798.0,
|
| 295 |
+
"eval_physics_runtime": 85.3386,
|
| 296 |
+
"eval_physics_samples_per_second": 5.859,
|
| 297 |
+
"eval_physics_steps_per_second": 1.465,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"entropy": 1.0462193094193935,
|
| 302 |
+
"epoch": 0.336,
|
| 303 |
+
"grad_norm": 11.875,
|
| 304 |
+
"learning_rate": 1.3933333333333334e-05,
|
| 305 |
+
"loss": 17.7296,
|
| 306 |
+
"mean_token_accuracy": 0.7623197592794895,
|
| 307 |
+
"num_tokens": 6953611.0,
|
| 308 |
+
"step": 210
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"entropy": 1.0164767142385245,
|
| 312 |
+
"epoch": 0.352,
|
| 313 |
+
"grad_norm": 11.25,
|
| 314 |
+
"learning_rate": 1.46e-05,
|
| 315 |
+
"loss": 17.1525,
|
| 316 |
+
"mean_token_accuracy": 0.7695928748697043,
|
| 317 |
+
"num_tokens": 7290378.0,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"entropy": 0.9987690806388855,
|
| 322 |
+
"epoch": 0.368,
|
| 323 |
+
"grad_norm": 11.4375,
|
| 324 |
+
"learning_rate": 1.5266666666666667e-05,
|
| 325 |
+
"loss": 16.9228,
|
| 326 |
+
"mean_token_accuracy": 0.7714470315724611,
|
| 327 |
+
"num_tokens": 7621082.0,
|
| 328 |
+
"step": 230
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"entropy": 1.0506686847656965,
|
| 332 |
+
"epoch": 0.384,
|
| 333 |
+
"grad_norm": 11.3125,
|
| 334 |
+
"learning_rate": 1.5933333333333336e-05,
|
| 335 |
+
"loss": 17.6416,
|
| 336 |
+
"mean_token_accuracy": 0.7599896423518657,
|
| 337 |
+
"num_tokens": 7955570.0,
|
| 338 |
+
"step": 240
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"entropy": 1.0135670874267817,
|
| 342 |
+
"epoch": 0.4,
|
| 343 |
+
"grad_norm": 14.5,
|
| 344 |
+
"learning_rate": 1.66e-05,
|
| 345 |
+
"loss": 16.9698,
|
| 346 |
+
"mean_token_accuracy": 0.7687441952526569,
|
| 347 |
+
"num_tokens": 8291049.0,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"entropy": 0.9876859273761511,
|
| 352 |
+
"epoch": 0.416,
|
| 353 |
+
"grad_norm": 13.75,
|
| 354 |
+
"learning_rate": 1.726666666666667e-05,
|
| 355 |
+
"loss": 16.6909,
|
| 356 |
+
"mean_token_accuracy": 0.7725014701485634,
|
| 357 |
+
"num_tokens": 8627310.0,
|
| 358 |
+
"step": 260
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"entropy": 1.0216444052755833,
|
| 362 |
+
"epoch": 0.432,
|
| 363 |
+
"grad_norm": 12.125,
|
| 364 |
+
"learning_rate": 1.7933333333333333e-05,
|
| 365 |
+
"loss": 17.011,
|
| 366 |
+
"mean_token_accuracy": 0.7689431305974722,
|
| 367 |
+
"num_tokens": 8958371.0,
|
| 368 |
+
"step": 270
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"entropy": 0.9649551097303629,
|
| 372 |
+
"epoch": 0.448,
|
| 373 |
+
"grad_norm": 12.1875,
|
| 374 |
+
"learning_rate": 1.86e-05,
|
| 375 |
+
"loss": 16.2252,
|
| 376 |
+
"mean_token_accuracy": 0.7780237648636102,
|
| 377 |
+
"num_tokens": 9294388.0,
|
| 378 |
+
"step": 280
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"entropy": 0.9653072291985154,
|
| 382 |
+
"epoch": 0.464,
|
| 383 |
+
"grad_norm": 12.5,
|
| 384 |
+
"learning_rate": 1.926666666666667e-05,
|
| 385 |
+
"loss": 16.1144,
|
| 386 |
+
"mean_token_accuracy": 0.7772431872785092,
|
| 387 |
+
"num_tokens": 9620366.0,
|
| 388 |
+
"step": 290
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"entropy": 0.9695413928478956,
|
| 392 |
+
"epoch": 0.48,
|
| 393 |
+
"grad_norm": 11.8125,
|
| 394 |
+
"learning_rate": 1.9933333333333334e-05,
|
| 395 |
+
"loss": 16.4447,
|
| 396 |
+
"mean_token_accuracy": 0.7733453687280416,
|
| 397 |
+
"num_tokens": 9955431.0,
|
| 398 |
+
"step": 300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.48,
|
| 402 |
+
"eval_biology_entropy": 2.7462952222824097,
|
| 403 |
+
"eval_biology_loss": 3.060053825378418,
|
| 404 |
+
"eval_biology_mean_token_accuracy": 0.5114872539043427,
|
| 405 |
+
"eval_biology_num_tokens": 9955431.0,
|
| 406 |
+
"eval_biology_runtime": 56.9805,
|
| 407 |
+
"eval_biology_samples_per_second": 8.775,
|
| 408 |
+
"eval_biology_steps_per_second": 2.194,
|
| 409 |
+
"step": 300
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.48,
|
| 413 |
+
"eval_chemistry_entropy": 1.3710836601257324,
|
| 414 |
+
"eval_chemistry_loss": 1.4066872596740723,
|
| 415 |
+
"eval_chemistry_mean_token_accuracy": 0.7168692064285278,
|
| 416 |
+
"eval_chemistry_num_tokens": 9955431.0,
|
| 417 |
+
"eval_chemistry_runtime": 71.3717,
|
| 418 |
+
"eval_chemistry_samples_per_second": 7.006,
|
| 419 |
+
"eval_chemistry_steps_per_second": 1.751,
|
| 420 |
+
"step": 300
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.48,
|
| 424 |
+
"eval_math_entropy": 0.9784291224479675,
|
| 425 |
+
"eval_math_loss": 1.2082456350326538,
|
| 426 |
+
"eval_math_mean_token_accuracy": 0.7478420066833497,
|
| 427 |
+
"eval_math_num_tokens": 9955431.0,
|
| 428 |
+
"eval_math_runtime": 74.3706,
|
| 429 |
+
"eval_math_samples_per_second": 6.723,
|
| 430 |
+
"eval_math_steps_per_second": 1.681,
|
| 431 |
+
"step": 300
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.48,
|
| 435 |
+
"eval_physics_entropy": 1.007008915424347,
|
| 436 |
+
"eval_physics_loss": 1.0401662588119507,
|
| 437 |
+
"eval_physics_mean_token_accuracy": 0.7707204632759094,
|
| 438 |
+
"eval_physics_num_tokens": 9955431.0,
|
| 439 |
+
"eval_physics_runtime": 84.6939,
|
| 440 |
+
"eval_physics_samples_per_second": 5.904,
|
| 441 |
+
"eval_physics_steps_per_second": 1.476,
|
| 442 |
+
"step": 300
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"entropy": 1.007104156538844,
|
| 446 |
+
"epoch": 0.496,
|
| 447 |
+
"grad_norm": 10.5,
|
| 448 |
+
"learning_rate": 1.9933333333333334e-05,
|
| 449 |
+
"loss": 16.6639,
|
| 450 |
+
"mean_token_accuracy": 0.771253039687872,
|
| 451 |
+
"num_tokens": 10289883.0,
|
| 452 |
+
"step": 310
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"entropy": 0.9723599992692471,
|
| 456 |
+
"epoch": 0.512,
|
| 457 |
+
"grad_norm": 12.4375,
|
| 458 |
+
"learning_rate": 1.985925925925926e-05,
|
| 459 |
+
"loss": 16.4387,
|
| 460 |
+
"mean_token_accuracy": 0.7748051699250936,
|
| 461 |
+
"num_tokens": 10619468.0,
|
| 462 |
+
"step": 320
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"entropy": 0.9979474730789661,
|
| 466 |
+
"epoch": 0.528,
|
| 467 |
+
"grad_norm": 10.8125,
|
| 468 |
+
"learning_rate": 1.9785185185185187e-05,
|
| 469 |
+
"loss": 16.6398,
|
| 470 |
+
"mean_token_accuracy": 0.7712166555225849,
|
| 471 |
+
"num_tokens": 10944904.0,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"entropy": 0.9800913408398628,
|
| 476 |
+
"epoch": 0.544,
|
| 477 |
+
"grad_norm": 11.625,
|
| 478 |
+
"learning_rate": 1.971111111111111e-05,
|
| 479 |
+
"loss": 16.374,
|
| 480 |
+
"mean_token_accuracy": 0.7737775973975658,
|
| 481 |
+
"num_tokens": 11266409.0,
|
| 482 |
+
"step": 340
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"entropy": 0.9599094491451978,
|
| 486 |
+
"epoch": 0.56,
|
| 487 |
+
"grad_norm": 10.625,
|
| 488 |
+
"learning_rate": 1.963703703703704e-05,
|
| 489 |
+
"loss": 16.0194,
|
| 490 |
+
"mean_token_accuracy": 0.778597004711628,
|
| 491 |
+
"num_tokens": 11605544.0,
|
| 492 |
+
"step": 350
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"entropy": 0.948445113003254,
|
| 496 |
+
"epoch": 0.576,
|
| 497 |
+
"grad_norm": 11.75,
|
| 498 |
+
"learning_rate": 1.9562962962962964e-05,
|
| 499 |
+
"loss": 15.9791,
|
| 500 |
+
"mean_token_accuracy": 0.7805619373917579,
|
| 501 |
+
"num_tokens": 11931715.0,
|
| 502 |
+
"step": 360
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"entropy": 0.9618662863969802,
|
| 506 |
+
"epoch": 0.592,
|
| 507 |
+
"grad_norm": 13.0625,
|
| 508 |
+
"learning_rate": 1.948888888888889e-05,
|
| 509 |
+
"loss": 16.0713,
|
| 510 |
+
"mean_token_accuracy": 0.776887471601367,
|
| 511 |
+
"num_tokens": 12257243.0,
|
| 512 |
+
"step": 370
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"entropy": 0.9480277199298144,
|
| 516 |
+
"epoch": 0.608,
|
| 517 |
+
"grad_norm": 10.8125,
|
| 518 |
+
"learning_rate": 1.9414814814814817e-05,
|
| 519 |
+
"loss": 15.8656,
|
| 520 |
+
"mean_token_accuracy": 0.7797395702451467,
|
| 521 |
+
"num_tokens": 12583154.0,
|
| 522 |
+
"step": 380
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"entropy": 0.9716805059462785,
|
| 526 |
+
"epoch": 0.624,
|
| 527 |
+
"grad_norm": 10.625,
|
| 528 |
+
"learning_rate": 1.9340740740740743e-05,
|
| 529 |
+
"loss": 16.1886,
|
| 530 |
+
"mean_token_accuracy": 0.7762768242508173,
|
| 531 |
+
"num_tokens": 12905392.0,
|
| 532 |
+
"step": 390
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"entropy": 0.9691856369376183,
|
| 536 |
+
"epoch": 0.64,
|
| 537 |
+
"grad_norm": 11.8125,
|
| 538 |
+
"learning_rate": 1.926666666666667e-05,
|
| 539 |
+
"loss": 16.2314,
|
| 540 |
+
"mean_token_accuracy": 0.7761619180440903,
|
| 541 |
+
"num_tokens": 13232198.0,
|
| 542 |
+
"step": 400
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.64,
|
| 546 |
+
"eval_biology_entropy": 2.67273916721344,
|
| 547 |
+
"eval_biology_loss": 2.96358585357666,
|
| 548 |
+
"eval_biology_mean_token_accuracy": 0.5216054661273957,
|
| 549 |
+
"eval_biology_num_tokens": 13232198.0,
|
| 550 |
+
"eval_biology_runtime": 57.8851,
|
| 551 |
+
"eval_biology_samples_per_second": 8.638,
|
| 552 |
+
"eval_biology_steps_per_second": 2.159,
|
| 553 |
+
"step": 400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.64,
|
| 557 |
+
"eval_chemistry_entropy": 1.3173069462776184,
|
| 558 |
+
"eval_chemistry_loss": 1.36112380027771,
|
| 559 |
+
"eval_chemistry_mean_token_accuracy": 0.7232093935012818,
|
| 560 |
+
"eval_chemistry_num_tokens": 13232198.0,
|
| 561 |
+
"eval_chemistry_runtime": 71.8687,
|
| 562 |
+
"eval_chemistry_samples_per_second": 6.957,
|
| 563 |
+
"eval_chemistry_steps_per_second": 1.739,
|
| 564 |
+
"step": 400
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.64,
|
| 568 |
+
"eval_math_entropy": 0.9528153438568115,
|
| 569 |
+
"eval_math_loss": 1.1841319799423218,
|
| 570 |
+
"eval_math_mean_token_accuracy": 0.7507999067306519,
|
| 571 |
+
"eval_math_num_tokens": 13232198.0,
|
| 572 |
+
"eval_math_runtime": 74.8756,
|
| 573 |
+
"eval_math_samples_per_second": 6.678,
|
| 574 |
+
"eval_math_steps_per_second": 1.669,
|
| 575 |
+
"step": 400
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.64,
|
| 579 |
+
"eval_physics_entropy": 0.9614342203140259,
|
| 580 |
+
"eval_physics_loss": 1.0016775131225586,
|
| 581 |
+
"eval_physics_mean_token_accuracy": 0.7765112986564636,
|
| 582 |
+
"eval_physics_num_tokens": 13232198.0,
|
| 583 |
+
"eval_physics_runtime": 85.1175,
|
| 584 |
+
"eval_physics_samples_per_second": 5.874,
|
| 585 |
+
"eval_physics_steps_per_second": 1.469,
|
| 586 |
+
"step": 400
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.9530647125095129,
|
| 590 |
+
"epoch": 0.656,
|
| 591 |
+
"grad_norm": 11.375,
|
| 592 |
+
"learning_rate": 1.9192592592592593e-05,
|
| 593 |
+
"loss": 15.9429,
|
| 594 |
+
"mean_token_accuracy": 0.7780249908566474,
|
| 595 |
+
"num_tokens": 13575902.0,
|
| 596 |
+
"step": 410
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.9399624351412058,
|
| 600 |
+
"epoch": 0.672,
|
| 601 |
+
"grad_norm": 12.0625,
|
| 602 |
+
"learning_rate": 1.911851851851852e-05,
|
| 603 |
+
"loss": 15.7284,
|
| 604 |
+
"mean_token_accuracy": 0.7817466016858816,
|
| 605 |
+
"num_tokens": 13895997.0,
|
| 606 |
+
"step": 420
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 0.9540142439305782,
|
| 610 |
+
"epoch": 0.688,
|
| 611 |
+
"grad_norm": 10.6875,
|
| 612 |
+
"learning_rate": 1.9044444444444446e-05,
|
| 613 |
+
"loss": 15.7763,
|
| 614 |
+
"mean_token_accuracy": 0.7817316662520171,
|
| 615 |
+
"num_tokens": 14234888.0,
|
| 616 |
+
"step": 430
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 0.9538515221327544,
|
| 620 |
+
"epoch": 0.704,
|
| 621 |
+
"grad_norm": 11.625,
|
| 622 |
+
"learning_rate": 1.8970370370370372e-05,
|
| 623 |
+
"loss": 16.0838,
|
| 624 |
+
"mean_token_accuracy": 0.775813952833414,
|
| 625 |
+
"num_tokens": 14567908.0,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 0.9464580094441771,
|
| 630 |
+
"epoch": 0.72,
|
| 631 |
+
"grad_norm": 12.375,
|
| 632 |
+
"learning_rate": 1.8896296296296295e-05,
|
| 633 |
+
"loss": 15.704,
|
| 634 |
+
"mean_token_accuracy": 0.7821726374328136,
|
| 635 |
+
"num_tokens": 14882927.0,
|
| 636 |
+
"step": 450
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 0.9363573594018817,
|
| 640 |
+
"epoch": 0.736,
|
| 641 |
+
"grad_norm": 13.0625,
|
| 642 |
+
"learning_rate": 1.8822222222222225e-05,
|
| 643 |
+
"loss": 15.7075,
|
| 644 |
+
"mean_token_accuracy": 0.7809599131345749,
|
| 645 |
+
"num_tokens": 15217342.0,
|
| 646 |
+
"step": 460
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 0.9193624388426542,
|
| 650 |
+
"epoch": 0.752,
|
| 651 |
+
"grad_norm": 10.4375,
|
| 652 |
+
"learning_rate": 1.874814814814815e-05,
|
| 653 |
+
"loss": 15.3677,
|
| 654 |
+
"mean_token_accuracy": 0.7846659943461418,
|
| 655 |
+
"num_tokens": 15547710.0,
|
| 656 |
+
"step": 470
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 0.9613647162914276,
|
| 660 |
+
"epoch": 0.768,
|
| 661 |
+
"grad_norm": 11.1875,
|
| 662 |
+
"learning_rate": 1.8674074074074075e-05,
|
| 663 |
+
"loss": 16.0934,
|
| 664 |
+
"mean_token_accuracy": 0.7759233452379704,
|
| 665 |
+
"num_tokens": 15877177.0,
|
| 666 |
+
"step": 480
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"entropy": 0.9139260027557612,
|
| 670 |
+
"epoch": 0.784,
|
| 671 |
+
"grad_norm": 10.1875,
|
| 672 |
+
"learning_rate": 1.86e-05,
|
| 673 |
+
"loss": 15.3216,
|
| 674 |
+
"mean_token_accuracy": 0.786144433543086,
|
| 675 |
+
"num_tokens": 16219640.0,
|
| 676 |
+
"step": 490
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"entropy": 0.9349881060421467,
|
| 680 |
+
"epoch": 0.8,
|
| 681 |
+
"grad_norm": 12.0,
|
| 682 |
+
"learning_rate": 1.8525925925925928e-05,
|
| 683 |
+
"loss": 15.6534,
|
| 684 |
+
"mean_token_accuracy": 0.7819662269204855,
|
| 685 |
+
"num_tokens": 16548261.0,
|
| 686 |
+
"step": 500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8,
|
| 690 |
+
"eval_biology_entropy": 2.617759398460388,
|
| 691 |
+
"eval_biology_loss": 2.9445557594299316,
|
| 692 |
+
"eval_biology_mean_token_accuracy": 0.5238966343402862,
|
| 693 |
+
"eval_biology_num_tokens": 16548261.0,
|
| 694 |
+
"eval_biology_runtime": 57.6905,
|
| 695 |
+
"eval_biology_samples_per_second": 8.667,
|
| 696 |
+
"eval_biology_steps_per_second": 2.167,
|
| 697 |
+
"step": 500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8,
|
| 701 |
+
"eval_chemistry_entropy": 1.2937732858657838,
|
| 702 |
+
"eval_chemistry_loss": 1.3414490222930908,
|
| 703 |
+
"eval_chemistry_mean_token_accuracy": 0.7248484263420105,
|
| 704 |
+
"eval_chemistry_num_tokens": 16548261.0,
|
| 705 |
+
"eval_chemistry_runtime": 71.1659,
|
| 706 |
+
"eval_chemistry_samples_per_second": 7.026,
|
| 707 |
+
"eval_chemistry_steps_per_second": 1.756,
|
| 708 |
+
"step": 500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.8,
|
| 712 |
+
"eval_math_entropy": 0.93889684009552,
|
| 713 |
+
"eval_math_loss": 1.17385995388031,
|
| 714 |
+
"eval_math_mean_token_accuracy": 0.7522515163421631,
|
| 715 |
+
"eval_math_num_tokens": 16548261.0,
|
| 716 |
+
"eval_math_runtime": 74.7142,
|
| 717 |
+
"eval_math_samples_per_second": 6.692,
|
| 718 |
+
"eval_math_steps_per_second": 1.673,
|
| 719 |
+
"step": 500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.8,
|
| 723 |
+
"eval_physics_entropy": 0.9420124840736389,
|
| 724 |
+
"eval_physics_loss": 0.9809063673019409,
|
| 725 |
+
"eval_physics_mean_token_accuracy": 0.7797514395713806,
|
| 726 |
+
"eval_physics_num_tokens": 16548261.0,
|
| 727 |
+
"eval_physics_runtime": 84.5204,
|
| 728 |
+
"eval_physics_samples_per_second": 5.916,
|
| 729 |
+
"eval_physics_steps_per_second": 1.479,
|
| 730 |
+
"step": 500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 0.9288215478882194,
|
| 734 |
+
"epoch": 0.816,
|
| 735 |
+
"grad_norm": 11.3125,
|
| 736 |
+
"learning_rate": 1.8451851851851855e-05,
|
| 737 |
+
"loss": 15.5725,
|
| 738 |
+
"mean_token_accuracy": 0.7813547737896442,
|
| 739 |
+
"num_tokens": 16870533.0,
|
| 740 |
+
"step": 510
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 0.9446330968290567,
|
| 744 |
+
"epoch": 0.832,
|
| 745 |
+
"grad_norm": 15.875,
|
| 746 |
+
"learning_rate": 1.8377777777777778e-05,
|
| 747 |
+
"loss": 15.7952,
|
| 748 |
+
"mean_token_accuracy": 0.7800830528140068,
|
| 749 |
+
"num_tokens": 17196371.0,
|
| 750 |
+
"step": 520
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 0.9318377874791622,
|
| 754 |
+
"epoch": 0.848,
|
| 755 |
+
"grad_norm": 10.625,
|
| 756 |
+
"learning_rate": 1.8303703703703704e-05,
|
| 757 |
+
"loss": 15.4484,
|
| 758 |
+
"mean_token_accuracy": 0.7836398217827082,
|
| 759 |
+
"num_tokens": 17527066.0,
|
| 760 |
+
"step": 530
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 0.9298348639160394,
|
| 764 |
+
"epoch": 0.864,
|
| 765 |
+
"grad_norm": 10.625,
|
| 766 |
+
"learning_rate": 1.822962962962963e-05,
|
| 767 |
+
"loss": 15.6026,
|
| 768 |
+
"mean_token_accuracy": 0.7814645994454622,
|
| 769 |
+
"num_tokens": 17859605.0,
|
| 770 |
+
"step": 540
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 0.9549105998128653,
|
| 774 |
+
"epoch": 0.88,
|
| 775 |
+
"grad_norm": 12.625,
|
| 776 |
+
"learning_rate": 1.8155555555555557e-05,
|
| 777 |
+
"loss": 15.7997,
|
| 778 |
+
"mean_token_accuracy": 0.7805559232831001,
|
| 779 |
+
"num_tokens": 18187315.0,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 0.8820257507264614,
|
| 784 |
+
"epoch": 0.896,
|
| 785 |
+
"grad_norm": 10.5625,
|
| 786 |
+
"learning_rate": 1.8081481481481484e-05,
|
| 787 |
+
"loss": 14.7783,
|
| 788 |
+
"mean_token_accuracy": 0.7907331828027964,
|
| 789 |
+
"num_tokens": 18536790.0,
|
| 790 |
+
"step": 560
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 0.9362711973488331,
|
| 794 |
+
"epoch": 0.912,
|
| 795 |
+
"grad_norm": 12.5625,
|
| 796 |
+
"learning_rate": 1.800740740740741e-05,
|
| 797 |
+
"loss": 15.6226,
|
| 798 |
+
"mean_token_accuracy": 0.7802051860839129,
|
| 799 |
+
"num_tokens": 18869344.0,
|
| 800 |
+
"step": 570
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 0.9295620009303093,
|
| 804 |
+
"epoch": 0.928,
|
| 805 |
+
"grad_norm": 12.75,
|
| 806 |
+
"learning_rate": 1.7933333333333333e-05,
|
| 807 |
+
"loss": 15.5339,
|
| 808 |
+
"mean_token_accuracy": 0.7815026968717576,
|
| 809 |
+
"num_tokens": 19199834.0,
|
| 810 |
+
"step": 580
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 0.9112746389582753,
|
| 814 |
+
"epoch": 0.944,
|
| 815 |
+
"grad_norm": 12.5,
|
| 816 |
+
"learning_rate": 1.785925925925926e-05,
|
| 817 |
+
"loss": 15.2153,
|
| 818 |
+
"mean_token_accuracy": 0.7855059750378132,
|
| 819 |
+
"num_tokens": 19525385.0,
|
| 820 |
+
"step": 590
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 0.9181267462670804,
|
| 824 |
+
"epoch": 0.96,
|
| 825 |
+
"grad_norm": 12.75,
|
| 826 |
+
"learning_rate": 1.7785185185185186e-05,
|
| 827 |
+
"loss": 15.3751,
|
| 828 |
+
"mean_token_accuracy": 0.7829241104424,
|
| 829 |
+
"num_tokens": 19856973.0,
|
| 830 |
+
"step": 600
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.96,
|
| 834 |
+
"eval_biology_entropy": 2.594178828239441,
|
| 835 |
+
"eval_biology_loss": 2.9207751750946045,
|
| 836 |
+
"eval_biology_mean_token_accuracy": 0.5271391036510468,
|
| 837 |
+
"eval_biology_num_tokens": 19856973.0,
|
| 838 |
+
"eval_biology_runtime": 57.0207,
|
| 839 |
+
"eval_biology_samples_per_second": 8.769,
|
| 840 |
+
"eval_biology_steps_per_second": 2.192,
|
| 841 |
+
"step": 600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.96,
|
| 845 |
+
"eval_chemistry_entropy": 1.270768217086792,
|
| 846 |
+
"eval_chemistry_loss": 1.3242253065109253,
|
| 847 |
+
"eval_chemistry_mean_token_accuracy": 0.7280859136581421,
|
| 848 |
+
"eval_chemistry_num_tokens": 19856973.0,
|
| 849 |
+
"eval_chemistry_runtime": 72.006,
|
| 850 |
+
"eval_chemistry_samples_per_second": 6.944,
|
| 851 |
+
"eval_chemistry_steps_per_second": 1.736,
|
| 852 |
+
"step": 600
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.96,
|
| 856 |
+
"eval_math_entropy": 0.9325860266685486,
|
| 857 |
+
"eval_math_loss": 1.1655522584915161,
|
| 858 |
+
"eval_math_mean_token_accuracy": 0.7533689908981324,
|
| 859 |
+
"eval_math_num_tokens": 19856973.0,
|
| 860 |
+
"eval_math_runtime": 74.0585,
|
| 861 |
+
"eval_math_samples_per_second": 6.751,
|
| 862 |
+
"eval_math_steps_per_second": 1.688,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.96,
|
| 867 |
+
"eval_physics_entropy": 0.9269161529541016,
|
| 868 |
+
"eval_physics_loss": 0.9667912125587463,
|
| 869 |
+
"eval_physics_mean_token_accuracy": 0.7814396271705627,
|
| 870 |
+
"eval_physics_num_tokens": 19856973.0,
|
| 871 |
+
"eval_physics_runtime": 84.5863,
|
| 872 |
+
"eval_physics_samples_per_second": 5.911,
|
| 873 |
+
"eval_physics_steps_per_second": 1.478,
|
| 874 |
+
"step": 600
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"entropy": 0.9162795972079039,
|
| 878 |
+
"epoch": 0.976,
|
| 879 |
+
"grad_norm": 12.125,
|
| 880 |
+
"learning_rate": 1.7711111111111113e-05,
|
| 881 |
+
"loss": 15.2813,
|
| 882 |
+
"mean_token_accuracy": 0.7860829800367355,
|
| 883 |
+
"num_tokens": 20190600.0,
|
| 884 |
+
"step": 610
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"entropy": 0.9235894799232482,
|
| 888 |
+
"epoch": 0.992,
|
| 889 |
+
"grad_norm": 11.5,
|
| 890 |
+
"learning_rate": 1.763703703703704e-05,
|
| 891 |
+
"loss": 15.4241,
|
| 892 |
+
"mean_token_accuracy": 0.784028148651123,
|
| 893 |
+
"num_tokens": 20518014.0,
|
| 894 |
+
"step": 620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"entropy": 0.9041305113583803,
|
| 898 |
+
"epoch": 1.008,
|
| 899 |
+
"grad_norm": 11.0625,
|
| 900 |
+
"learning_rate": 1.7562962962962962e-05,
|
| 901 |
+
"loss": 14.9099,
|
| 902 |
+
"mean_token_accuracy": 0.7884359251707792,
|
| 903 |
+
"num_tokens": 20859215.0,
|
| 904 |
+
"step": 630
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"entropy": 0.9018714495003224,
|
| 908 |
+
"epoch": 1.024,
|
| 909 |
+
"grad_norm": 11.1875,
|
| 910 |
+
"learning_rate": 1.7488888888888892e-05,
|
| 911 |
+
"loss": 15.1658,
|
| 912 |
+
"mean_token_accuracy": 0.7857498530298471,
|
| 913 |
+
"num_tokens": 21186658.0,
|
| 914 |
+
"step": 640
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"entropy": 0.916073745302856,
|
| 918 |
+
"epoch": 1.04,
|
| 919 |
+
"grad_norm": 10.8125,
|
| 920 |
+
"learning_rate": 1.7414814814814815e-05,
|
| 921 |
+
"loss": 15.1367,
|
| 922 |
+
"mean_token_accuracy": 0.7867844242602586,
|
| 923 |
+
"num_tokens": 21517237.0,
|
| 924 |
+
"step": 650
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"entropy": 0.8802109774202108,
|
| 928 |
+
"epoch": 1.056,
|
| 929 |
+
"grad_norm": 11.0,
|
| 930 |
+
"learning_rate": 1.7340740740740742e-05,
|
| 931 |
+
"loss": 14.7961,
|
| 932 |
+
"mean_token_accuracy": 0.7896511305123568,
|
| 933 |
+
"num_tokens": 21852528.0,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"entropy": 0.9102928217500448,
|
| 938 |
+
"epoch": 1.072,
|
| 939 |
+
"grad_norm": 10.0,
|
| 940 |
+
"learning_rate": 1.726666666666667e-05,
|
| 941 |
+
"loss": 15.1014,
|
| 942 |
+
"mean_token_accuracy": 0.7862772591412067,
|
| 943 |
+
"num_tokens": 22192380.0,
|
| 944 |
+
"step": 670
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"entropy": 0.9107371259480714,
|
| 948 |
+
"epoch": 1.088,
|
| 949 |
+
"grad_norm": 13.4375,
|
| 950 |
+
"learning_rate": 1.7192592592592595e-05,
|
| 951 |
+
"loss": 15.2493,
|
| 952 |
+
"mean_token_accuracy": 0.7848471954464913,
|
| 953 |
+
"num_tokens": 22517971.0,
|
| 954 |
+
"step": 680
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"entropy": 0.8938208010047675,
|
| 958 |
+
"epoch": 1.104,
|
| 959 |
+
"grad_norm": 10.6875,
|
| 960 |
+
"learning_rate": 1.711851851851852e-05,
|
| 961 |
+
"loss": 14.9017,
|
| 962 |
+
"mean_token_accuracy": 0.7887144055217504,
|
| 963 |
+
"num_tokens": 22848694.0,
|
| 964 |
+
"step": 690
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"entropy": 0.9129897281527519,
|
| 968 |
+
"epoch": 1.12,
|
| 969 |
+
"grad_norm": 11.4375,
|
| 970 |
+
"learning_rate": 1.7044444444444445e-05,
|
| 971 |
+
"loss": 15.2722,
|
| 972 |
+
"mean_token_accuracy": 0.7840389590710402,
|
| 973 |
+
"num_tokens": 23183889.0,
|
| 974 |
+
"step": 700
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.12,
|
| 978 |
+
"eval_biology_entropy": 2.5242818908691405,
|
| 979 |
+
"eval_biology_loss": 2.9092111587524414,
|
| 980 |
+
"eval_biology_mean_token_accuracy": 0.5278490686416626,
|
| 981 |
+
"eval_biology_num_tokens": 23183889.0,
|
| 982 |
+
"eval_biology_runtime": 57.2117,
|
| 983 |
+
"eval_biology_samples_per_second": 8.739,
|
| 984 |
+
"eval_biology_steps_per_second": 2.185,
|
| 985 |
+
"step": 700
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.12,
|
| 989 |
+
"eval_chemistry_entropy": 1.2367294158935547,
|
| 990 |
+
"eval_chemistry_loss": 1.3155030012130737,
|
| 991 |
+
"eval_chemistry_mean_token_accuracy": 0.7286214451789856,
|
| 992 |
+
"eval_chemistry_num_tokens": 23183889.0,
|
| 993 |
+
"eval_chemistry_runtime": 71.8224,
|
| 994 |
+
"eval_chemistry_samples_per_second": 6.962,
|
| 995 |
+
"eval_chemistry_steps_per_second": 1.74,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.12,
|
| 1000 |
+
"eval_math_entropy": 0.9127886519432068,
|
| 1001 |
+
"eval_math_loss": 1.1603002548217773,
|
| 1002 |
+
"eval_math_mean_token_accuracy": 0.754603410243988,
|
| 1003 |
+
"eval_math_num_tokens": 23183889.0,
|
| 1004 |
+
"eval_math_runtime": 74.5403,
|
| 1005 |
+
"eval_math_samples_per_second": 6.708,
|
| 1006 |
+
"eval_math_steps_per_second": 1.677,
|
| 1007 |
+
"step": 700
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.12,
|
| 1011 |
+
"eval_physics_entropy": 0.9048804240226745,
|
| 1012 |
+
"eval_physics_loss": 0.9561019539833069,
|
| 1013 |
+
"eval_physics_mean_token_accuracy": 0.7832872924804688,
|
| 1014 |
+
"eval_physics_num_tokens": 23183889.0,
|
| 1015 |
+
"eval_physics_runtime": 84.6107,
|
| 1016 |
+
"eval_physics_samples_per_second": 5.909,
|
| 1017 |
+
"eval_physics_steps_per_second": 1.477,
|
| 1018 |
+
"step": 700
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"entropy": 0.8741975981742144,
|
| 1022 |
+
"epoch": 1.1360000000000001,
|
| 1023 |
+
"grad_norm": 10.1875,
|
| 1024 |
+
"learning_rate": 1.697037037037037e-05,
|
| 1025 |
+
"loss": 14.564,
|
| 1026 |
+
"mean_token_accuracy": 0.7930445209145546,
|
| 1027 |
+
"num_tokens": 23523903.0,
|
| 1028 |
+
"step": 710
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"entropy": 0.8917050797492265,
|
| 1032 |
+
"epoch": 1.152,
|
| 1033 |
+
"grad_norm": 12.75,
|
| 1034 |
+
"learning_rate": 1.6896296296296298e-05,
|
| 1035 |
+
"loss": 14.9557,
|
| 1036 |
+
"mean_token_accuracy": 0.7896463591605425,
|
| 1037 |
+
"num_tokens": 23848848.0,
|
| 1038 |
+
"step": 720
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"entropy": 0.9238279532641173,
|
| 1042 |
+
"epoch": 1.168,
|
| 1043 |
+
"grad_norm": 11.6875,
|
| 1044 |
+
"learning_rate": 1.6822222222222224e-05,
|
| 1045 |
+
"loss": 15.2756,
|
| 1046 |
+
"mean_token_accuracy": 0.7821665916591882,
|
| 1047 |
+
"num_tokens": 24174589.0,
|
| 1048 |
+
"step": 730
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"entropy": 0.9052068604156375,
|
| 1052 |
+
"epoch": 1.184,
|
| 1053 |
+
"grad_norm": 13.5625,
|
| 1054 |
+
"learning_rate": 1.6748148148148147e-05,
|
| 1055 |
+
"loss": 15.0924,
|
| 1056 |
+
"mean_token_accuracy": 0.7870742384344339,
|
| 1057 |
+
"num_tokens": 24495981.0,
|
| 1058 |
+
"step": 740
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"entropy": 0.877324876561761,
|
| 1062 |
+
"epoch": 1.2,
|
| 1063 |
+
"grad_norm": 11.1875,
|
| 1064 |
+
"learning_rate": 1.6674074074074077e-05,
|
| 1065 |
+
"loss": 14.7224,
|
| 1066 |
+
"mean_token_accuracy": 0.7919886518269778,
|
| 1067 |
+
"num_tokens": 24826245.0,
|
| 1068 |
+
"step": 750
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"entropy": 0.9162866469472647,
|
| 1072 |
+
"epoch": 1.216,
|
| 1073 |
+
"grad_norm": 14.1875,
|
| 1074 |
+
"learning_rate": 1.66e-05,
|
| 1075 |
+
"loss": 15.1252,
|
| 1076 |
+
"mean_token_accuracy": 0.7850615303963423,
|
| 1077 |
+
"num_tokens": 25147775.0,
|
| 1078 |
+
"step": 760
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"entropy": 0.8838450819253921,
|
| 1082 |
+
"epoch": 1.232,
|
| 1083 |
+
"grad_norm": 12.1875,
|
| 1084 |
+
"learning_rate": 1.6525925925925927e-05,
|
| 1085 |
+
"loss": 14.8829,
|
| 1086 |
+
"mean_token_accuracy": 0.7893829133361578,
|
| 1087 |
+
"num_tokens": 25480033.0,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"entropy": 0.8952008984982968,
|
| 1092 |
+
"epoch": 1.248,
|
| 1093 |
+
"grad_norm": 12.875,
|
| 1094 |
+
"learning_rate": 1.6451851851851853e-05,
|
| 1095 |
+
"loss": 14.9213,
|
| 1096 |
+
"mean_token_accuracy": 0.7889137178659439,
|
| 1097 |
+
"num_tokens": 25811978.0,
|
| 1098 |
+
"step": 780
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"entropy": 0.8893922835588455,
|
| 1102 |
+
"epoch": 1.264,
|
| 1103 |
+
"grad_norm": 12.6875,
|
| 1104 |
+
"learning_rate": 1.637777777777778e-05,
|
| 1105 |
+
"loss": 14.7989,
|
| 1106 |
+
"mean_token_accuracy": 0.7897166382521391,
|
| 1107 |
+
"num_tokens": 26146299.0,
|
| 1108 |
+
"step": 790
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"entropy": 0.9172267891466618,
|
| 1112 |
+
"epoch": 1.28,
|
| 1113 |
+
"grad_norm": 11.75,
|
| 1114 |
+
"learning_rate": 1.6303703703703706e-05,
|
| 1115 |
+
"loss": 15.3289,
|
| 1116 |
+
"mean_token_accuracy": 0.782142074778676,
|
| 1117 |
+
"num_tokens": 26478207.0,
|
| 1118 |
+
"step": 800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.28,
|
| 1122 |
+
"eval_biology_entropy": 2.5403532466888428,
|
| 1123 |
+
"eval_biology_loss": 2.9071850776672363,
|
| 1124 |
+
"eval_biology_mean_token_accuracy": 0.529075275182724,
|
| 1125 |
+
"eval_biology_num_tokens": 26478207.0,
|
| 1126 |
+
"eval_biology_runtime": 56.934,
|
| 1127 |
+
"eval_biology_samples_per_second": 8.782,
|
| 1128 |
+
"eval_biology_steps_per_second": 2.196,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.28,
|
| 1133 |
+
"eval_chemistry_entropy": 1.234187596321106,
|
| 1134 |
+
"eval_chemistry_loss": 1.306308388710022,
|
| 1135 |
+
"eval_chemistry_mean_token_accuracy": 0.7299280157089233,
|
| 1136 |
+
"eval_chemistry_num_tokens": 26478207.0,
|
| 1137 |
+
"eval_chemistry_runtime": 71.938,
|
| 1138 |
+
"eval_chemistry_samples_per_second": 6.95,
|
| 1139 |
+
"eval_chemistry_steps_per_second": 1.738,
|
| 1140 |
+
"step": 800
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.28,
|
| 1144 |
+
"eval_math_entropy": 0.9124487805366516,
|
| 1145 |
+
"eval_math_loss": 1.1551406383514404,
|
| 1146 |
+
"eval_math_mean_token_accuracy": 0.7556050124168396,
|
| 1147 |
+
"eval_math_num_tokens": 26478207.0,
|
| 1148 |
+
"eval_math_runtime": 75.1703,
|
| 1149 |
+
"eval_math_samples_per_second": 6.652,
|
| 1150 |
+
"eval_math_steps_per_second": 1.663,
|
| 1151 |
+
"step": 800
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.28,
|
| 1155 |
+
"eval_physics_entropy": 0.8998128218650818,
|
| 1156 |
+
"eval_physics_loss": 0.9489150047302246,
|
| 1157 |
+
"eval_physics_mean_token_accuracy": 0.7840672006607056,
|
| 1158 |
+
"eval_physics_num_tokens": 26478207.0,
|
| 1159 |
+
"eval_physics_runtime": 85.0147,
|
| 1160 |
+
"eval_physics_samples_per_second": 5.881,
|
| 1161 |
+
"eval_physics_steps_per_second": 1.47,
|
| 1162 |
+
"step": 800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"entropy": 0.8760543465614319,
|
| 1166 |
+
"epoch": 1.296,
|
| 1167 |
+
"grad_norm": 12.8125,
|
| 1168 |
+
"learning_rate": 1.622962962962963e-05,
|
| 1169 |
+
"loss": 14.6611,
|
| 1170 |
+
"mean_token_accuracy": 0.7923007346689701,
|
| 1171 |
+
"num_tokens": 26806477.0,
|
| 1172 |
+
"step": 810
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"entropy": 0.917656009271741,
|
| 1176 |
+
"epoch": 1.312,
|
| 1177 |
+
"grad_norm": 13.1875,
|
| 1178 |
+
"learning_rate": 1.6155555555555556e-05,
|
| 1179 |
+
"loss": 15.2379,
|
| 1180 |
+
"mean_token_accuracy": 0.7841715186834335,
|
| 1181 |
+
"num_tokens": 27137528.0,
|
| 1182 |
+
"step": 820
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"entropy": 0.8967037841677665,
|
| 1186 |
+
"epoch": 1.328,
|
| 1187 |
+
"grad_norm": 13.25,
|
| 1188 |
+
"learning_rate": 1.6081481481481482e-05,
|
| 1189 |
+
"loss": 14.9513,
|
| 1190 |
+
"mean_token_accuracy": 0.7878007985651493,
|
| 1191 |
+
"num_tokens": 27465859.0,
|
| 1192 |
+
"step": 830
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"entropy": 0.901091538183391,
|
| 1196 |
+
"epoch": 1.3439999999999999,
|
| 1197 |
+
"grad_norm": 13.375,
|
| 1198 |
+
"learning_rate": 1.600740740740741e-05,
|
| 1199 |
+
"loss": 15.1044,
|
| 1200 |
+
"mean_token_accuracy": 0.7861052300781012,
|
| 1201 |
+
"num_tokens": 27795568.0,
|
| 1202 |
+
"step": 840
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"entropy": 0.9121165912598371,
|
| 1206 |
+
"epoch": 1.3599999999999999,
|
| 1207 |
+
"grad_norm": 11.625,
|
| 1208 |
+
"learning_rate": 1.5933333333333336e-05,
|
| 1209 |
+
"loss": 15.0779,
|
| 1210 |
+
"mean_token_accuracy": 0.7859285034239292,
|
| 1211 |
+
"num_tokens": 28129988.0,
|
| 1212 |
+
"step": 850
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"entropy": 0.8819791020825505,
|
| 1216 |
+
"epoch": 1.376,
|
| 1217 |
+
"grad_norm": 13.875,
|
| 1218 |
+
"learning_rate": 1.5859259259259262e-05,
|
| 1219 |
+
"loss": 14.7997,
|
| 1220 |
+
"mean_token_accuracy": 0.7886631991714239,
|
| 1221 |
+
"num_tokens": 28465903.0,
|
| 1222 |
+
"step": 860
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"entropy": 0.8854727063328027,
|
| 1226 |
+
"epoch": 1.392,
|
| 1227 |
+
"grad_norm": 13.25,
|
| 1228 |
+
"learning_rate": 1.5785185185185185e-05,
|
| 1229 |
+
"loss": 14.61,
|
| 1230 |
+
"mean_token_accuracy": 0.7927087835967541,
|
| 1231 |
+
"num_tokens": 28801554.0,
|
| 1232 |
+
"step": 870
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"entropy": 0.8729526123031974,
|
| 1236 |
+
"epoch": 1.408,
|
| 1237 |
+
"grad_norm": 12.4375,
|
| 1238 |
+
"learning_rate": 1.571111111111111e-05,
|
| 1239 |
+
"loss": 14.7562,
|
| 1240 |
+
"mean_token_accuracy": 0.7899845536798239,
|
| 1241 |
+
"num_tokens": 29125114.0,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"entropy": 0.913954821228981,
|
| 1246 |
+
"epoch": 1.424,
|
| 1247 |
+
"grad_norm": 10.9375,
|
| 1248 |
+
"learning_rate": 1.5637037037037038e-05,
|
| 1249 |
+
"loss": 15.2188,
|
| 1250 |
+
"mean_token_accuracy": 0.783445942774415,
|
| 1251 |
+
"num_tokens": 29454334.0,
|
| 1252 |
+
"step": 890
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"entropy": 0.8652864851057529,
|
| 1256 |
+
"epoch": 1.44,
|
| 1257 |
+
"grad_norm": 12.1875,
|
| 1258 |
+
"learning_rate": 1.5562962962962965e-05,
|
| 1259 |
+
"loss": 14.3528,
|
| 1260 |
+
"mean_token_accuracy": 0.794481047987938,
|
| 1261 |
+
"num_tokens": 29789253.0,
|
| 1262 |
+
"step": 900
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.44,
|
| 1266 |
+
"eval_biology_entropy": 2.4760996789932253,
|
| 1267 |
+
"eval_biology_loss": 2.897955894470215,
|
| 1268 |
+
"eval_biology_mean_token_accuracy": 0.5296812095642089,
|
| 1269 |
+
"eval_biology_num_tokens": 29789253.0,
|
| 1270 |
+
"eval_biology_runtime": 57.0842,
|
| 1271 |
+
"eval_biology_samples_per_second": 8.759,
|
| 1272 |
+
"eval_biology_steps_per_second": 2.19,
|
| 1273 |
+
"step": 900
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.44,
|
| 1277 |
+
"eval_chemistry_entropy": 1.2120891718864442,
|
| 1278 |
+
"eval_chemistry_loss": 1.2991372346878052,
|
| 1279 |
+
"eval_chemistry_mean_token_accuracy": 0.7307901701927185,
|
| 1280 |
+
"eval_chemistry_num_tokens": 29789253.0,
|
| 1281 |
+
"eval_chemistry_runtime": 71.5779,
|
| 1282 |
+
"eval_chemistry_samples_per_second": 6.985,
|
| 1283 |
+
"eval_chemistry_steps_per_second": 1.746,
|
| 1284 |
+
"step": 900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.44,
|
| 1288 |
+
"eval_math_entropy": 0.9021294908523559,
|
| 1289 |
+
"eval_math_loss": 1.1532059907913208,
|
| 1290 |
+
"eval_math_mean_token_accuracy": 0.755294855594635,
|
| 1291 |
+
"eval_math_num_tokens": 29789253.0,
|
| 1292 |
+
"eval_math_runtime": 74.8641,
|
| 1293 |
+
"eval_math_samples_per_second": 6.679,
|
| 1294 |
+
"eval_math_steps_per_second": 1.67,
|
| 1295 |
+
"step": 900
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.44,
|
| 1299 |
+
"eval_physics_entropy": 0.8853664617538453,
|
| 1300 |
+
"eval_physics_loss": 0.9413084983825684,
|
| 1301 |
+
"eval_physics_mean_token_accuracy": 0.7854379539489746,
|
| 1302 |
+
"eval_physics_num_tokens": 29789253.0,
|
| 1303 |
+
"eval_physics_runtime": 84.3345,
|
| 1304 |
+
"eval_physics_samples_per_second": 5.929,
|
| 1305 |
+
"eval_physics_steps_per_second": 1.482,
|
| 1306 |
+
"step": 900
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"entropy": 0.8592871313914656,
|
| 1310 |
+
"epoch": 1.456,
|
| 1311 |
+
"grad_norm": 10.5,
|
| 1312 |
+
"learning_rate": 1.548888888888889e-05,
|
| 1313 |
+
"loss": 14.4092,
|
| 1314 |
+
"mean_token_accuracy": 0.7947866775095462,
|
| 1315 |
+
"num_tokens": 30128576.0,
|
| 1316 |
+
"step": 910
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"entropy": 0.9165356293320656,
|
| 1320 |
+
"epoch": 1.472,
|
| 1321 |
+
"grad_norm": 12.8125,
|
| 1322 |
+
"learning_rate": 1.5414814814814814e-05,
|
| 1323 |
+
"loss": 15.368,
|
| 1324 |
+
"mean_token_accuracy": 0.7829437594860792,
|
| 1325 |
+
"num_tokens": 30452719.0,
|
| 1326 |
+
"step": 920
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"entropy": 0.9012311644852161,
|
| 1330 |
+
"epoch": 1.488,
|
| 1331 |
+
"grad_norm": 10.9375,
|
| 1332 |
+
"learning_rate": 1.5340740740740744e-05,
|
| 1333 |
+
"loss": 14.9137,
|
| 1334 |
+
"mean_token_accuracy": 0.7879349775612354,
|
| 1335 |
+
"num_tokens": 30782343.0,
|
| 1336 |
+
"step": 930
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"entropy": 0.8793585889041424,
|
| 1340 |
+
"epoch": 1.504,
|
| 1341 |
+
"grad_norm": 11.75,
|
| 1342 |
+
"learning_rate": 1.5266666666666667e-05,
|
| 1343 |
+
"loss": 14.6612,
|
| 1344 |
+
"mean_token_accuracy": 0.7913552910089493,
|
| 1345 |
+
"num_tokens": 31113238.0,
|
| 1346 |
+
"step": 940
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"entropy": 0.896404268220067,
|
| 1350 |
+
"epoch": 1.52,
|
| 1351 |
+
"grad_norm": 12.25,
|
| 1352 |
+
"learning_rate": 1.5192592592592594e-05,
|
| 1353 |
+
"loss": 15.0177,
|
| 1354 |
+
"mean_token_accuracy": 0.7869206938892603,
|
| 1355 |
+
"num_tokens": 31444589.0,
|
| 1356 |
+
"step": 950
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"entropy": 0.9115363927558064,
|
| 1360 |
+
"epoch": 1.536,
|
| 1361 |
+
"grad_norm": 13.625,
|
| 1362 |
+
"learning_rate": 1.5118518518518519e-05,
|
| 1363 |
+
"loss": 15.1508,
|
| 1364 |
+
"mean_token_accuracy": 0.7850655887275935,
|
| 1365 |
+
"num_tokens": 31774137.0,
|
| 1366 |
+
"step": 960
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"entropy": 0.8715274870395661,
|
| 1370 |
+
"epoch": 1.552,
|
| 1371 |
+
"grad_norm": 12.5,
|
| 1372 |
+
"learning_rate": 1.5044444444444445e-05,
|
| 1373 |
+
"loss": 14.4724,
|
| 1374 |
+
"mean_token_accuracy": 0.7919801536947488,
|
| 1375 |
+
"num_tokens": 32101776.0,
|
| 1376 |
+
"step": 970
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"entropy": 0.8716113748028874,
|
| 1380 |
+
"epoch": 1.568,
|
| 1381 |
+
"grad_norm": 11.9375,
|
| 1382 |
+
"learning_rate": 1.497037037037037e-05,
|
| 1383 |
+
"loss": 14.5441,
|
| 1384 |
+
"mean_token_accuracy": 0.7928904049098492,
|
| 1385 |
+
"num_tokens": 32428021.0,
|
| 1386 |
+
"step": 980
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"entropy": 0.9078653456643224,
|
| 1390 |
+
"epoch": 1.584,
|
| 1391 |
+
"grad_norm": 12.375,
|
| 1392 |
+
"learning_rate": 1.4896296296296298e-05,
|
| 1393 |
+
"loss": 15.1365,
|
| 1394 |
+
"mean_token_accuracy": 0.7834811493754387,
|
| 1395 |
+
"num_tokens": 32752735.0,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"entropy": 0.8948801588267088,
|
| 1400 |
+
"epoch": 1.6,
|
| 1401 |
+
"grad_norm": 11.4375,
|
| 1402 |
+
"learning_rate": 1.4822222222222225e-05,
|
| 1403 |
+
"loss": 14.975,
|
| 1404 |
+
"mean_token_accuracy": 0.7872815534472466,
|
| 1405 |
+
"num_tokens": 33075822.0,
|
| 1406 |
+
"step": 1000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.6,
|
| 1410 |
+
"eval_biology_entropy": 2.508749726295471,
|
| 1411 |
+
"eval_biology_loss": 2.8778915405273438,
|
| 1412 |
+
"eval_biology_mean_token_accuracy": 0.5310802006721497,
|
| 1413 |
+
"eval_biology_num_tokens": 33075822.0,
|
| 1414 |
+
"eval_biology_runtime": 57.246,
|
| 1415 |
+
"eval_biology_samples_per_second": 8.734,
|
| 1416 |
+
"eval_biology_steps_per_second": 2.184,
|
| 1417 |
+
"step": 1000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.6,
|
| 1421 |
+
"eval_chemistry_entropy": 1.2282180700302123,
|
| 1422 |
+
"eval_chemistry_loss": 1.2942099571228027,
|
| 1423 |
+
"eval_chemistry_mean_token_accuracy": 0.7318216099739074,
|
| 1424 |
+
"eval_chemistry_num_tokens": 33075822.0,
|
| 1425 |
+
"eval_chemistry_runtime": 71.0784,
|
| 1426 |
+
"eval_chemistry_samples_per_second": 7.034,
|
| 1427 |
+
"eval_chemistry_steps_per_second": 1.759,
|
| 1428 |
+
"step": 1000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.6,
|
| 1432 |
+
"eval_math_entropy": 0.9116221733093262,
|
| 1433 |
+
"eval_math_loss": 1.1501303911209106,
|
| 1434 |
+
"eval_math_mean_token_accuracy": 0.7557219748497009,
|
| 1435 |
+
"eval_math_num_tokens": 33075822.0,
|
| 1436 |
+
"eval_math_runtime": 74.8337,
|
| 1437 |
+
"eval_math_samples_per_second": 6.681,
|
| 1438 |
+
"eval_math_steps_per_second": 1.67,
|
| 1439 |
+
"step": 1000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.6,
|
| 1443 |
+
"eval_physics_entropy": 0.8932713055610657,
|
| 1444 |
+
"eval_physics_loss": 0.9365818500518799,
|
| 1445 |
+
"eval_physics_mean_token_accuracy": 0.785537106513977,
|
| 1446 |
+
"eval_physics_num_tokens": 33075822.0,
|
| 1447 |
+
"eval_physics_runtime": 84.6443,
|
| 1448 |
+
"eval_physics_samples_per_second": 5.907,
|
| 1449 |
+
"eval_physics_steps_per_second": 1.477,
|
| 1450 |
+
"step": 1000
|
| 1451 |
+
}
|
| 1452 |
+
],
|
| 1453 |
+
"logging_steps": 10,
|
| 1454 |
+
"max_steps": 3000,
|
| 1455 |
+
"num_input_tokens_seen": 0,
|
| 1456 |
+
"num_train_epochs": 5,
|
| 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": 3.3005113980506685e+18,
|
| 1471 |
+
"train_batch_size": 4,
|
| 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 sha256:931abe455d5684f7fdb033d2616f7c607fe28af43a0be9856fe4a9c238858acc
|
| 3 |
+
size 6417
|