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:c71ea45e35e951fce66a73f3bd5a7e53251fd32691ee94b977f9915d0304b5f6
|
| 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:d6ae52088181b23c5926ed15c090146b9a47cd292ad3cd52f4855edc1a01af6f
|
| 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:f7c9a9d8bdc5d4e8b686144ede2793ebb174d23a2aea04395ecf5cc4fbf73a27
|
| 3 |
+
size 1793214689
|
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": 1.1280501924455166,
|
| 14 |
+
"epoch": 0.016,
|
| 15 |
+
"grad_norm": 161.0,
|
| 16 |
+
"learning_rate": 6.000000000000001e-07,
|
| 17 |
+
"loss": 36.0968,
|
| 18 |
+
"mean_token_accuracy": 0.6165979273617268,
|
| 19 |
+
"num_tokens": 280941.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.1705728020519017,
|
| 24 |
+
"epoch": 0.032,
|
| 25 |
+
"grad_norm": 146.0,
|
| 26 |
+
"learning_rate": 1.2666666666666669e-06,
|
| 27 |
+
"loss": 36.5572,
|
| 28 |
+
"mean_token_accuracy": 0.6121777599677444,
|
| 29 |
+
"num_tokens": 558056.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.1892314109951259,
|
| 34 |
+
"epoch": 0.048,
|
| 35 |
+
"grad_norm": 135.0,
|
| 36 |
+
"learning_rate": 1.9333333333333336e-06,
|
| 37 |
+
"loss": 35.5667,
|
| 38 |
+
"mean_token_accuracy": 0.6162483215332031,
|
| 39 |
+
"num_tokens": 836753.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.2923907738178968,
|
| 44 |
+
"epoch": 0.064,
|
| 45 |
+
"grad_norm": 106.0,
|
| 46 |
+
"learning_rate": 2.6e-06,
|
| 47 |
+
"loss": 34.4747,
|
| 48 |
+
"mean_token_accuracy": 0.6145394820719957,
|
| 49 |
+
"num_tokens": 1126446.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 1.4465828079730272,
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"grad_norm": 86.5,
|
| 56 |
+
"learning_rate": 3.266666666666667e-06,
|
| 57 |
+
"loss": 32.2616,
|
| 58 |
+
"mean_token_accuracy": 0.6272102266550064,
|
| 59 |
+
"num_tokens": 1413596.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 1.5344239331781864,
|
| 64 |
+
"epoch": 0.096,
|
| 65 |
+
"grad_norm": 54.25,
|
| 66 |
+
"learning_rate": 3.9333333333333335e-06,
|
| 67 |
+
"loss": 28.8152,
|
| 68 |
+
"mean_token_accuracy": 0.6551170501857996,
|
| 69 |
+
"num_tokens": 1701193.0,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.5569457441568375,
|
| 74 |
+
"epoch": 0.112,
|
| 75 |
+
"grad_norm": 45.75,
|
| 76 |
+
"learning_rate": 4.600000000000001e-06,
|
| 77 |
+
"loss": 26.6094,
|
| 78 |
+
"mean_token_accuracy": 0.6667167004197836,
|
| 79 |
+
"num_tokens": 1979232.0,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 1.4980619736015797,
|
| 84 |
+
"epoch": 0.128,
|
| 85 |
+
"grad_norm": 34.0,
|
| 86 |
+
"learning_rate": 5.2666666666666665e-06,
|
| 87 |
+
"loss": 25.0735,
|
| 88 |
+
"mean_token_accuracy": 0.6823939502239227,
|
| 89 |
+
"num_tokens": 2274177.0,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.4427384316921235,
|
| 94 |
+
"epoch": 0.144,
|
| 95 |
+
"grad_norm": 29.75,
|
| 96 |
+
"learning_rate": 5.933333333333335e-06,
|
| 97 |
+
"loss": 23.2103,
|
| 98 |
+
"mean_token_accuracy": 0.6962548345327377,
|
| 99 |
+
"num_tokens": 2548445.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.3565625827759504,
|
| 104 |
+
"epoch": 0.16,
|
| 105 |
+
"grad_norm": 30.875,
|
| 106 |
+
"learning_rate": 6.600000000000001e-06,
|
| 107 |
+
"loss": 21.4845,
|
| 108 |
+
"mean_token_accuracy": 0.7108539894223214,
|
| 109 |
+
"num_tokens": 2824418.0,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.16,
|
| 114 |
+
"eval_biology_entropy": 3.535919818878174,
|
| 115 |
+
"eval_biology_loss": 5.02457332611084,
|
| 116 |
+
"eval_biology_mean_token_accuracy": 0.3542800180912018,
|
| 117 |
+
"eval_biology_num_tokens": 2824418.0,
|
| 118 |
+
"eval_biology_runtime": 49.6437,
|
| 119 |
+
"eval_biology_samples_per_second": 10.072,
|
| 120 |
+
"eval_biology_steps_per_second": 2.518,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.16,
|
| 125 |
+
"eval_chemistry_entropy": 2.5280555896759034,
|
| 126 |
+
"eval_chemistry_loss": 2.8887903690338135,
|
| 127 |
+
"eval_chemistry_mean_token_accuracy": 0.5300401592254639,
|
| 128 |
+
"eval_chemistry_num_tokens": 2824418.0,
|
| 129 |
+
"eval_chemistry_runtime": 61.5471,
|
| 130 |
+
"eval_chemistry_samples_per_second": 8.124,
|
| 131 |
+
"eval_chemistry_steps_per_second": 2.031,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.16,
|
| 136 |
+
"eval_math_entropy": 1.3736235461235047,
|
| 137 |
+
"eval_math_loss": 1.3470827341079712,
|
| 138 |
+
"eval_math_mean_token_accuracy": 0.7081305732727051,
|
| 139 |
+
"eval_math_num_tokens": 2824418.0,
|
| 140 |
+
"eval_math_runtime": 63.1282,
|
| 141 |
+
"eval_math_samples_per_second": 7.92,
|
| 142 |
+
"eval_math_steps_per_second": 1.98,
|
| 143 |
+
"step": 100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.16,
|
| 147 |
+
"eval_physics_entropy": 2.064271595954895,
|
| 148 |
+
"eval_physics_loss": 2.1881864070892334,
|
| 149 |
+
"eval_physics_mean_token_accuracy": 0.6055651969909668,
|
| 150 |
+
"eval_physics_num_tokens": 2824418.0,
|
| 151 |
+
"eval_physics_runtime": 71.8769,
|
| 152 |
+
"eval_physics_samples_per_second": 6.956,
|
| 153 |
+
"eval_physics_steps_per_second": 1.739,
|
| 154 |
+
"step": 100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"entropy": 1.3322576396167278,
|
| 158 |
+
"epoch": 0.176,
|
| 159 |
+
"grad_norm": 23.25,
|
| 160 |
+
"learning_rate": 7.266666666666668e-06,
|
| 161 |
+
"loss": 20.9108,
|
| 162 |
+
"mean_token_accuracy": 0.7151085637509823,
|
| 163 |
+
"num_tokens": 3110313.0,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"entropy": 1.3247066088020802,
|
| 168 |
+
"epoch": 0.192,
|
| 169 |
+
"grad_norm": 23.625,
|
| 170 |
+
"learning_rate": 7.933333333333334e-06,
|
| 171 |
+
"loss": 20.6356,
|
| 172 |
+
"mean_token_accuracy": 0.7142969533801079,
|
| 173 |
+
"num_tokens": 3394170.0,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"entropy": 1.256456857919693,
|
| 178 |
+
"epoch": 0.208,
|
| 179 |
+
"grad_norm": 21.125,
|
| 180 |
+
"learning_rate": 8.6e-06,
|
| 181 |
+
"loss": 19.9583,
|
| 182 |
+
"mean_token_accuracy": 0.7226813279092312,
|
| 183 |
+
"num_tokens": 3673600.0,
|
| 184 |
+
"step": 130
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"entropy": 1.2233942866325378,
|
| 188 |
+
"epoch": 0.224,
|
| 189 |
+
"grad_norm": 23.5,
|
| 190 |
+
"learning_rate": 9.266666666666667e-06,
|
| 191 |
+
"loss": 19.4829,
|
| 192 |
+
"mean_token_accuracy": 0.7258789885789156,
|
| 193 |
+
"num_tokens": 3953732.0,
|
| 194 |
+
"step": 140
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"entropy": 1.1788023415952922,
|
| 198 |
+
"epoch": 0.24,
|
| 199 |
+
"grad_norm": 22.625,
|
| 200 |
+
"learning_rate": 9.933333333333334e-06,
|
| 201 |
+
"loss": 18.6617,
|
| 202 |
+
"mean_token_accuracy": 0.735758152604103,
|
| 203 |
+
"num_tokens": 4243655.0,
|
| 204 |
+
"step": 150
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"entropy": 1.1358939699828625,
|
| 208 |
+
"epoch": 0.256,
|
| 209 |
+
"grad_norm": 21.25,
|
| 210 |
+
"learning_rate": 1.0600000000000002e-05,
|
| 211 |
+
"loss": 18.067,
|
| 212 |
+
"mean_token_accuracy": 0.7414251279085875,
|
| 213 |
+
"num_tokens": 4531471.0,
|
| 214 |
+
"step": 160
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"entropy": 1.1413200695067645,
|
| 218 |
+
"epoch": 0.272,
|
| 219 |
+
"grad_norm": 18.75,
|
| 220 |
+
"learning_rate": 1.1266666666666668e-05,
|
| 221 |
+
"loss": 18.2054,
|
| 222 |
+
"mean_token_accuracy": 0.740831508487463,
|
| 223 |
+
"num_tokens": 4810284.0,
|
| 224 |
+
"step": 170
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"entropy": 1.125382575765252,
|
| 228 |
+
"epoch": 0.288,
|
| 229 |
+
"grad_norm": 17.875,
|
| 230 |
+
"learning_rate": 1.1933333333333335e-05,
|
| 231 |
+
"loss": 17.7696,
|
| 232 |
+
"mean_token_accuracy": 0.7443546559661627,
|
| 233 |
+
"num_tokens": 5095104.0,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"entropy": 1.1154642656445504,
|
| 238 |
+
"epoch": 0.304,
|
| 239 |
+
"grad_norm": 17.125,
|
| 240 |
+
"learning_rate": 1.2600000000000001e-05,
|
| 241 |
+
"loss": 17.7511,
|
| 242 |
+
"mean_token_accuracy": 0.7442465547472239,
|
| 243 |
+
"num_tokens": 5383732.0,
|
| 244 |
+
"step": 190
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"entropy": 1.0828186847269534,
|
| 248 |
+
"epoch": 0.32,
|
| 249 |
+
"grad_norm": 19.875,
|
| 250 |
+
"learning_rate": 1.3266666666666668e-05,
|
| 251 |
+
"loss": 17.2671,
|
| 252 |
+
"mean_token_accuracy": 0.7503975994884968,
|
| 253 |
+
"num_tokens": 5676334.0,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.32,
|
| 258 |
+
"eval_biology_entropy": 3.6005834312438965,
|
| 259 |
+
"eval_biology_loss": 4.470179557800293,
|
| 260 |
+
"eval_biology_mean_token_accuracy": 0.3823731031417847,
|
| 261 |
+
"eval_biology_num_tokens": 5676334.0,
|
| 262 |
+
"eval_biology_runtime": 49.5338,
|
| 263 |
+
"eval_biology_samples_per_second": 10.094,
|
| 264 |
+
"eval_biology_steps_per_second": 2.524,
|
| 265 |
+
"step": 200
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.32,
|
| 269 |
+
"eval_chemistry_entropy": 2.351666664123535,
|
| 270 |
+
"eval_chemistry_loss": 2.5015459060668945,
|
| 271 |
+
"eval_chemistry_mean_token_accuracy": 0.5612157773971558,
|
| 272 |
+
"eval_chemistry_num_tokens": 5676334.0,
|
| 273 |
+
"eval_chemistry_runtime": 61.4417,
|
| 274 |
+
"eval_chemistry_samples_per_second": 8.138,
|
| 275 |
+
"eval_chemistry_steps_per_second": 2.034,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.32,
|
| 280 |
+
"eval_math_entropy": 1.1107734112739562,
|
| 281 |
+
"eval_math_loss": 1.1035394668579102,
|
| 282 |
+
"eval_math_mean_token_accuracy": 0.744808388710022,
|
| 283 |
+
"eval_math_num_tokens": 5676334.0,
|
| 284 |
+
"eval_math_runtime": 63.0675,
|
| 285 |
+
"eval_math_samples_per_second": 7.928,
|
| 286 |
+
"eval_math_steps_per_second": 1.982,
|
| 287 |
+
"step": 200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.32,
|
| 291 |
+
"eval_physics_entropy": 1.8196128549575805,
|
| 292 |
+
"eval_physics_loss": 1.8889656066894531,
|
| 293 |
+
"eval_physics_mean_token_accuracy": 0.6360980491638184,
|
| 294 |
+
"eval_physics_num_tokens": 5676334.0,
|
| 295 |
+
"eval_physics_runtime": 71.7937,
|
| 296 |
+
"eval_physics_samples_per_second": 6.964,
|
| 297 |
+
"eval_physics_steps_per_second": 1.741,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"entropy": 1.0973670542240144,
|
| 302 |
+
"epoch": 0.336,
|
| 303 |
+
"grad_norm": 19.0,
|
| 304 |
+
"learning_rate": 1.3933333333333334e-05,
|
| 305 |
+
"loss": 17.6111,
|
| 306 |
+
"mean_token_accuracy": 0.7442069798707962,
|
| 307 |
+
"num_tokens": 5958480.0,
|
| 308 |
+
"step": 210
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"entropy": 1.064722668007016,
|
| 312 |
+
"epoch": 0.352,
|
| 313 |
+
"grad_norm": 18.25,
|
| 314 |
+
"learning_rate": 1.46e-05,
|
| 315 |
+
"loss": 16.8683,
|
| 316 |
+
"mean_token_accuracy": 0.752158772200346,
|
| 317 |
+
"num_tokens": 6242161.0,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"entropy": 1.0617528311908244,
|
| 322 |
+
"epoch": 0.368,
|
| 323 |
+
"grad_norm": 20.5,
|
| 324 |
+
"learning_rate": 1.5266666666666667e-05,
|
| 325 |
+
"loss": 16.9997,
|
| 326 |
+
"mean_token_accuracy": 0.751146937161684,
|
| 327 |
+
"num_tokens": 6523679.0,
|
| 328 |
+
"step": 230
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"entropy": 1.0443669583648443,
|
| 332 |
+
"epoch": 0.384,
|
| 333 |
+
"grad_norm": 19.625,
|
| 334 |
+
"learning_rate": 1.5933333333333336e-05,
|
| 335 |
+
"loss": 16.6591,
|
| 336 |
+
"mean_token_accuracy": 0.7551476296037436,
|
| 337 |
+
"num_tokens": 6810978.0,
|
| 338 |
+
"step": 240
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"entropy": 1.0753562293946743,
|
| 342 |
+
"epoch": 0.4,
|
| 343 |
+
"grad_norm": 17.875,
|
| 344 |
+
"learning_rate": 1.66e-05,
|
| 345 |
+
"loss": 17.4353,
|
| 346 |
+
"mean_token_accuracy": 0.7485508523881436,
|
| 347 |
+
"num_tokens": 7096903.0,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"entropy": 1.0416356481611728,
|
| 352 |
+
"epoch": 0.416,
|
| 353 |
+
"grad_norm": 17.375,
|
| 354 |
+
"learning_rate": 1.726666666666667e-05,
|
| 355 |
+
"loss": 16.623,
|
| 356 |
+
"mean_token_accuracy": 0.7539484884589911,
|
| 357 |
+
"num_tokens": 7377181.0,
|
| 358 |
+
"step": 260
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"entropy": 1.0091398146003485,
|
| 362 |
+
"epoch": 0.432,
|
| 363 |
+
"grad_norm": 20.375,
|
| 364 |
+
"learning_rate": 1.7933333333333333e-05,
|
| 365 |
+
"loss": 16.1553,
|
| 366 |
+
"mean_token_accuracy": 0.7619809154421091,
|
| 367 |
+
"num_tokens": 7650523.0,
|
| 368 |
+
"step": 270
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"entropy": 0.9927664395421744,
|
| 372 |
+
"epoch": 0.448,
|
| 373 |
+
"grad_norm": 20.75,
|
| 374 |
+
"learning_rate": 1.86e-05,
|
| 375 |
+
"loss": 15.9549,
|
| 376 |
+
"mean_token_accuracy": 0.7623589888215065,
|
| 377 |
+
"num_tokens": 7936788.0,
|
| 378 |
+
"step": 280
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"entropy": 0.9981700140982867,
|
| 382 |
+
"epoch": 0.464,
|
| 383 |
+
"grad_norm": 21.75,
|
| 384 |
+
"learning_rate": 1.926666666666667e-05,
|
| 385 |
+
"loss": 16.1264,
|
| 386 |
+
"mean_token_accuracy": 0.761608887091279,
|
| 387 |
+
"num_tokens": 8223147.0,
|
| 388 |
+
"step": 290
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"entropy": 1.0235895983874799,
|
| 392 |
+
"epoch": 0.48,
|
| 393 |
+
"grad_norm": 19.375,
|
| 394 |
+
"learning_rate": 1.9933333333333334e-05,
|
| 395 |
+
"loss": 16.2896,
|
| 396 |
+
"mean_token_accuracy": 0.7603169117122889,
|
| 397 |
+
"num_tokens": 8506030.0,
|
| 398 |
+
"step": 300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.48,
|
| 402 |
+
"eval_biology_entropy": 3.66986682510376,
|
| 403 |
+
"eval_biology_loss": 4.148224353790283,
|
| 404 |
+
"eval_biology_mean_token_accuracy": 0.3987880692481995,
|
| 405 |
+
"eval_biology_num_tokens": 8506030.0,
|
| 406 |
+
"eval_biology_runtime": 49.5301,
|
| 407 |
+
"eval_biology_samples_per_second": 10.095,
|
| 408 |
+
"eval_biology_steps_per_second": 2.524,
|
| 409 |
+
"step": 300
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.48,
|
| 413 |
+
"eval_chemistry_entropy": 2.309468500137329,
|
| 414 |
+
"eval_chemistry_loss": 2.3434462547302246,
|
| 415 |
+
"eval_chemistry_mean_token_accuracy": 0.5782731935977936,
|
| 416 |
+
"eval_chemistry_num_tokens": 8506030.0,
|
| 417 |
+
"eval_chemistry_runtime": 61.4332,
|
| 418 |
+
"eval_chemistry_samples_per_second": 8.139,
|
| 419 |
+
"eval_chemistry_steps_per_second": 2.035,
|
| 420 |
+
"step": 300
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.48,
|
| 424 |
+
"eval_math_entropy": 1.007653223514557,
|
| 425 |
+
"eval_math_loss": 1.0127896070480347,
|
| 426 |
+
"eval_math_mean_token_accuracy": 0.7593745794296265,
|
| 427 |
+
"eval_math_num_tokens": 8506030.0,
|
| 428 |
+
"eval_math_runtime": 63.0217,
|
| 429 |
+
"eval_math_samples_per_second": 7.934,
|
| 430 |
+
"eval_math_steps_per_second": 1.983,
|
| 431 |
+
"step": 300
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.48,
|
| 435 |
+
"eval_physics_entropy": 1.7608964786529542,
|
| 436 |
+
"eval_physics_loss": 1.7697628736495972,
|
| 437 |
+
"eval_physics_mean_token_accuracy": 0.6516191956996917,
|
| 438 |
+
"eval_physics_num_tokens": 8506030.0,
|
| 439 |
+
"eval_physics_runtime": 71.8045,
|
| 440 |
+
"eval_physics_samples_per_second": 6.963,
|
| 441 |
+
"eval_physics_steps_per_second": 1.741,
|
| 442 |
+
"step": 300
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"entropy": 0.9751624643802643,
|
| 446 |
+
"epoch": 0.496,
|
| 447 |
+
"grad_norm": 27.0,
|
| 448 |
+
"learning_rate": 1.9933333333333334e-05,
|
| 449 |
+
"loss": 15.6472,
|
| 450 |
+
"mean_token_accuracy": 0.7660828057676554,
|
| 451 |
+
"num_tokens": 8788726.0,
|
| 452 |
+
"step": 310
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"entropy": 0.9841579314321279,
|
| 456 |
+
"epoch": 0.512,
|
| 457 |
+
"grad_norm": 19.5,
|
| 458 |
+
"learning_rate": 1.985925925925926e-05,
|
| 459 |
+
"loss": 15.7341,
|
| 460 |
+
"mean_token_accuracy": 0.765475382655859,
|
| 461 |
+
"num_tokens": 9078039.0,
|
| 462 |
+
"step": 320
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"entropy": 0.9567954104393721,
|
| 466 |
+
"epoch": 0.528,
|
| 467 |
+
"grad_norm": 22.875,
|
| 468 |
+
"learning_rate": 1.9785185185185187e-05,
|
| 469 |
+
"loss": 15.3963,
|
| 470 |
+
"mean_token_accuracy": 0.7705613534897566,
|
| 471 |
+
"num_tokens": 9373860.0,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"entropy": 0.9622254882007837,
|
| 476 |
+
"epoch": 0.544,
|
| 477 |
+
"grad_norm": 20.625,
|
| 478 |
+
"learning_rate": 1.971111111111111e-05,
|
| 479 |
+
"loss": 15.6284,
|
| 480 |
+
"mean_token_accuracy": 0.7682077161967754,
|
| 481 |
+
"num_tokens": 9660940.0,
|
| 482 |
+
"step": 340
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"entropy": 1.013891428336501,
|
| 486 |
+
"epoch": 0.56,
|
| 487 |
+
"grad_norm": 28.875,
|
| 488 |
+
"learning_rate": 1.963703703703704e-05,
|
| 489 |
+
"loss": 16.1123,
|
| 490 |
+
"mean_token_accuracy": 0.758896803110838,
|
| 491 |
+
"num_tokens": 9932302.0,
|
| 492 |
+
"step": 350
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"entropy": 0.9643709316849709,
|
| 496 |
+
"epoch": 0.576,
|
| 497 |
+
"grad_norm": 20.0,
|
| 498 |
+
"learning_rate": 1.9562962962962964e-05,
|
| 499 |
+
"loss": 15.4925,
|
| 500 |
+
"mean_token_accuracy": 0.7669644717127084,
|
| 501 |
+
"num_tokens": 10215462.0,
|
| 502 |
+
"step": 360
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"entropy": 0.9496656563133001,
|
| 506 |
+
"epoch": 0.592,
|
| 507 |
+
"grad_norm": 18.5,
|
| 508 |
+
"learning_rate": 1.948888888888889e-05,
|
| 509 |
+
"loss": 15.3772,
|
| 510 |
+
"mean_token_accuracy": 0.7689070332795381,
|
| 511 |
+
"num_tokens": 10504396.0,
|
| 512 |
+
"step": 370
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"entropy": 0.9635139308869839,
|
| 516 |
+
"epoch": 0.608,
|
| 517 |
+
"grad_norm": 17.5,
|
| 518 |
+
"learning_rate": 1.9414814814814817e-05,
|
| 519 |
+
"loss": 15.4665,
|
| 520 |
+
"mean_token_accuracy": 0.768926914036274,
|
| 521 |
+
"num_tokens": 10793126.0,
|
| 522 |
+
"step": 380
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"entropy": 0.9394328493624926,
|
| 526 |
+
"epoch": 0.624,
|
| 527 |
+
"grad_norm": 19.375,
|
| 528 |
+
"learning_rate": 1.9340740740740743e-05,
|
| 529 |
+
"loss": 15.1417,
|
| 530 |
+
"mean_token_accuracy": 0.7703750677406788,
|
| 531 |
+
"num_tokens": 11081768.0,
|
| 532 |
+
"step": 390
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"entropy": 0.930184380710125,
|
| 536 |
+
"epoch": 0.64,
|
| 537 |
+
"grad_norm": 18.25,
|
| 538 |
+
"learning_rate": 1.926666666666667e-05,
|
| 539 |
+
"loss": 14.8657,
|
| 540 |
+
"mean_token_accuracy": 0.7726314965635538,
|
| 541 |
+
"num_tokens": 11370320.0,
|
| 542 |
+
"step": 400
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.64,
|
| 546 |
+
"eval_biology_entropy": 3.578768089294434,
|
| 547 |
+
"eval_biology_loss": 4.099727630615234,
|
| 548 |
+
"eval_biology_mean_token_accuracy": 0.4042117977142334,
|
| 549 |
+
"eval_biology_num_tokens": 11370320.0,
|
| 550 |
+
"eval_biology_runtime": 49.5083,
|
| 551 |
+
"eval_biology_samples_per_second": 10.099,
|
| 552 |
+
"eval_biology_steps_per_second": 2.525,
|
| 553 |
+
"step": 400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.64,
|
| 557 |
+
"eval_chemistry_entropy": 2.1963028135299685,
|
| 558 |
+
"eval_chemistry_loss": 2.250903367996216,
|
| 559 |
+
"eval_chemistry_mean_token_accuracy": 0.588011109828949,
|
| 560 |
+
"eval_chemistry_num_tokens": 11370320.0,
|
| 561 |
+
"eval_chemistry_runtime": 61.4213,
|
| 562 |
+
"eval_chemistry_samples_per_second": 8.14,
|
| 563 |
+
"eval_chemistry_steps_per_second": 2.035,
|
| 564 |
+
"step": 400
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.64,
|
| 568 |
+
"eval_math_entropy": 0.9574988222122193,
|
| 569 |
+
"eval_math_loss": 0.9642173051834106,
|
| 570 |
+
"eval_math_mean_token_accuracy": 0.7676870808601379,
|
| 571 |
+
"eval_math_num_tokens": 11370320.0,
|
| 572 |
+
"eval_math_runtime": 62.9918,
|
| 573 |
+
"eval_math_samples_per_second": 7.938,
|
| 574 |
+
"eval_math_steps_per_second": 1.984,
|
| 575 |
+
"step": 400
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.64,
|
| 579 |
+
"eval_physics_entropy": 1.6637140741348266,
|
| 580 |
+
"eval_physics_loss": 1.7104088068008423,
|
| 581 |
+
"eval_physics_mean_token_accuracy": 0.6602483534812927,
|
| 582 |
+
"eval_physics_num_tokens": 11370320.0,
|
| 583 |
+
"eval_physics_runtime": 71.7644,
|
| 584 |
+
"eval_physics_samples_per_second": 6.967,
|
| 585 |
+
"eval_physics_steps_per_second": 1.742,
|
| 586 |
+
"step": 400
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.908730499073863,
|
| 590 |
+
"epoch": 0.656,
|
| 591 |
+
"grad_norm": 16.625,
|
| 592 |
+
"learning_rate": 1.9192592592592593e-05,
|
| 593 |
+
"loss": 14.6477,
|
| 594 |
+
"mean_token_accuracy": 0.7755995105952025,
|
| 595 |
+
"num_tokens": 11657835.0,
|
| 596 |
+
"step": 410
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.9500968560576439,
|
| 600 |
+
"epoch": 0.672,
|
| 601 |
+
"grad_norm": 18.25,
|
| 602 |
+
"learning_rate": 1.911851851851852e-05,
|
| 603 |
+
"loss": 15.2383,
|
| 604 |
+
"mean_token_accuracy": 0.769153194501996,
|
| 605 |
+
"num_tokens": 11949262.0,
|
| 606 |
+
"step": 420
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 0.9080810055136681,
|
| 610 |
+
"epoch": 0.688,
|
| 611 |
+
"grad_norm": 15.625,
|
| 612 |
+
"learning_rate": 1.9044444444444446e-05,
|
| 613 |
+
"loss": 14.6139,
|
| 614 |
+
"mean_token_accuracy": 0.7764004003256559,
|
| 615 |
+
"num_tokens": 12227640.0,
|
| 616 |
+
"step": 430
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 0.9170140367001295,
|
| 620 |
+
"epoch": 0.704,
|
| 621 |
+
"grad_norm": 17.625,
|
| 622 |
+
"learning_rate": 1.8970370370370372e-05,
|
| 623 |
+
"loss": 14.7655,
|
| 624 |
+
"mean_token_accuracy": 0.7752966023981571,
|
| 625 |
+
"num_tokens": 12516641.0,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 0.9368526700884103,
|
| 630 |
+
"epoch": 0.72,
|
| 631 |
+
"grad_norm": 19.25,
|
| 632 |
+
"learning_rate": 1.8896296296296295e-05,
|
| 633 |
+
"loss": 15.134,
|
| 634 |
+
"mean_token_accuracy": 0.7706776697188615,
|
| 635 |
+
"num_tokens": 12793343.0,
|
| 636 |
+
"step": 450
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 0.9261821806430817,
|
| 640 |
+
"epoch": 0.736,
|
| 641 |
+
"grad_norm": 17.5,
|
| 642 |
+
"learning_rate": 1.8822222222222225e-05,
|
| 643 |
+
"loss": 14.833,
|
| 644 |
+
"mean_token_accuracy": 0.7745088890194893,
|
| 645 |
+
"num_tokens": 13077981.0,
|
| 646 |
+
"step": 460
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 0.9040410481393337,
|
| 650 |
+
"epoch": 0.752,
|
| 651 |
+
"grad_norm": 19.75,
|
| 652 |
+
"learning_rate": 1.874814814814815e-05,
|
| 653 |
+
"loss": 14.4907,
|
| 654 |
+
"mean_token_accuracy": 0.7791126936674118,
|
| 655 |
+
"num_tokens": 13358957.0,
|
| 656 |
+
"step": 470
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 0.8739457067102194,
|
| 660 |
+
"epoch": 0.768,
|
| 661 |
+
"grad_norm": 15.8125,
|
| 662 |
+
"learning_rate": 1.8674074074074075e-05,
|
| 663 |
+
"loss": 14.112,
|
| 664 |
+
"mean_token_accuracy": 0.7853138707578182,
|
| 665 |
+
"num_tokens": 13653412.0,
|
| 666 |
+
"step": 480
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"entropy": 0.946398203074932,
|
| 670 |
+
"epoch": 0.784,
|
| 671 |
+
"grad_norm": 19.875,
|
| 672 |
+
"learning_rate": 1.86e-05,
|
| 673 |
+
"loss": 15.145,
|
| 674 |
+
"mean_token_accuracy": 0.7723897945135831,
|
| 675 |
+
"num_tokens": 13940856.0,
|
| 676 |
+
"step": 490
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"entropy": 0.9361972361803055,
|
| 680 |
+
"epoch": 0.8,
|
| 681 |
+
"grad_norm": 19.625,
|
| 682 |
+
"learning_rate": 1.8525925925925928e-05,
|
| 683 |
+
"loss": 15.2105,
|
| 684 |
+
"mean_token_accuracy": 0.7712519209831953,
|
| 685 |
+
"num_tokens": 14230754.0,
|
| 686 |
+
"step": 500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8,
|
| 690 |
+
"eval_biology_entropy": 3.714933115005493,
|
| 691 |
+
"eval_biology_loss": 3.970184564590454,
|
| 692 |
+
"eval_biology_mean_token_accuracy": 0.41206827068328855,
|
| 693 |
+
"eval_biology_num_tokens": 14230754.0,
|
| 694 |
+
"eval_biology_runtime": 49.5281,
|
| 695 |
+
"eval_biology_samples_per_second": 10.095,
|
| 696 |
+
"eval_biology_steps_per_second": 2.524,
|
| 697 |
+
"step": 500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8,
|
| 701 |
+
"eval_chemistry_entropy": 2.237494807243347,
|
| 702 |
+
"eval_chemistry_loss": 2.1822235584259033,
|
| 703 |
+
"eval_chemistry_mean_token_accuracy": 0.5956678519248962,
|
| 704 |
+
"eval_chemistry_num_tokens": 14230754.0,
|
| 705 |
+
"eval_chemistry_runtime": 61.0757,
|
| 706 |
+
"eval_chemistry_samples_per_second": 8.187,
|
| 707 |
+
"eval_chemistry_steps_per_second": 2.047,
|
| 708 |
+
"step": 500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.8,
|
| 712 |
+
"eval_math_entropy": 0.9503358464241027,
|
| 713 |
+
"eval_math_loss": 0.9351838827133179,
|
| 714 |
+
"eval_math_mean_token_accuracy": 0.7728546581268311,
|
| 715 |
+
"eval_math_num_tokens": 14230754.0,
|
| 716 |
+
"eval_math_runtime": 63.0753,
|
| 717 |
+
"eval_math_samples_per_second": 7.927,
|
| 718 |
+
"eval_math_steps_per_second": 1.982,
|
| 719 |
+
"step": 500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.8,
|
| 723 |
+
"eval_physics_entropy": 1.6920014672279358,
|
| 724 |
+
"eval_physics_loss": 1.671562671661377,
|
| 725 |
+
"eval_physics_mean_token_accuracy": 0.6658579094409942,
|
| 726 |
+
"eval_physics_num_tokens": 14230754.0,
|
| 727 |
+
"eval_physics_runtime": 71.8921,
|
| 728 |
+
"eval_physics_samples_per_second": 6.955,
|
| 729 |
+
"eval_physics_steps_per_second": 1.739,
|
| 730 |
+
"step": 500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 0.9170173428952694,
|
| 734 |
+
"epoch": 0.816,
|
| 735 |
+
"grad_norm": 18.625,
|
| 736 |
+
"learning_rate": 1.8451851851851855e-05,
|
| 737 |
+
"loss": 14.5639,
|
| 738 |
+
"mean_token_accuracy": 0.7766096990555524,
|
| 739 |
+
"num_tokens": 14519893.0,
|
| 740 |
+
"step": 510
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 0.9109945900738239,
|
| 744 |
+
"epoch": 0.832,
|
| 745 |
+
"grad_norm": 18.5,
|
| 746 |
+
"learning_rate": 1.8377777777777778e-05,
|
| 747 |
+
"loss": 14.6409,
|
| 748 |
+
"mean_token_accuracy": 0.7777223017066717,
|
| 749 |
+
"num_tokens": 14805088.0,
|
| 750 |
+
"step": 520
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 0.9337830897420645,
|
| 754 |
+
"epoch": 0.848,
|
| 755 |
+
"grad_norm": 19.0,
|
| 756 |
+
"learning_rate": 1.8303703703703704e-05,
|
| 757 |
+
"loss": 15.0412,
|
| 758 |
+
"mean_token_accuracy": 0.7716363571584225,
|
| 759 |
+
"num_tokens": 15086306.0,
|
| 760 |
+
"step": 530
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 0.9221564382314682,
|
| 764 |
+
"epoch": 0.864,
|
| 765 |
+
"grad_norm": 15.8125,
|
| 766 |
+
"learning_rate": 1.822962962962963e-05,
|
| 767 |
+
"loss": 14.7588,
|
| 768 |
+
"mean_token_accuracy": 0.7748291842639446,
|
| 769 |
+
"num_tokens": 15370985.0,
|
| 770 |
+
"step": 540
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 0.9273673612624407,
|
| 774 |
+
"epoch": 0.88,
|
| 775 |
+
"grad_norm": 21.0,
|
| 776 |
+
"learning_rate": 1.8155555555555557e-05,
|
| 777 |
+
"loss": 14.9233,
|
| 778 |
+
"mean_token_accuracy": 0.7736149989068508,
|
| 779 |
+
"num_tokens": 15653836.0,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 0.9161856021732092,
|
| 784 |
+
"epoch": 0.896,
|
| 785 |
+
"grad_norm": 21.75,
|
| 786 |
+
"learning_rate": 1.8081481481481484e-05,
|
| 787 |
+
"loss": 14.7618,
|
| 788 |
+
"mean_token_accuracy": 0.7746457736939192,
|
| 789 |
+
"num_tokens": 15932179.0,
|
| 790 |
+
"step": 560
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 0.8957702405750751,
|
| 794 |
+
"epoch": 0.912,
|
| 795 |
+
"grad_norm": 18.75,
|
| 796 |
+
"learning_rate": 1.800740740740741e-05,
|
| 797 |
+
"loss": 14.2902,
|
| 798 |
+
"mean_token_accuracy": 0.7794793792068958,
|
| 799 |
+
"num_tokens": 16219842.0,
|
| 800 |
+
"step": 570
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 0.8888734232634306,
|
| 804 |
+
"epoch": 0.928,
|
| 805 |
+
"grad_norm": 20.875,
|
| 806 |
+
"learning_rate": 1.7933333333333333e-05,
|
| 807 |
+
"loss": 14.2919,
|
| 808 |
+
"mean_token_accuracy": 0.7802723813802004,
|
| 809 |
+
"num_tokens": 16499842.0,
|
| 810 |
+
"step": 580
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 0.9097447639331222,
|
| 814 |
+
"epoch": 0.944,
|
| 815 |
+
"grad_norm": 35.0,
|
| 816 |
+
"learning_rate": 1.785925925925926e-05,
|
| 817 |
+
"loss": 14.7214,
|
| 818 |
+
"mean_token_accuracy": 0.7760318968445062,
|
| 819 |
+
"num_tokens": 16781882.0,
|
| 820 |
+
"step": 590
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 0.9282805230468512,
|
| 824 |
+
"epoch": 0.96,
|
| 825 |
+
"grad_norm": 16.125,
|
| 826 |
+
"learning_rate": 1.7785185185185186e-05,
|
| 827 |
+
"loss": 14.8274,
|
| 828 |
+
"mean_token_accuracy": 0.7749283302575349,
|
| 829 |
+
"num_tokens": 17067407.0,
|
| 830 |
+
"step": 600
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.96,
|
| 834 |
+
"eval_biology_entropy": 3.4800376834869384,
|
| 835 |
+
"eval_biology_loss": 3.9260165691375732,
|
| 836 |
+
"eval_biology_mean_token_accuracy": 0.41479419231414794,
|
| 837 |
+
"eval_biology_num_tokens": 17067407.0,
|
| 838 |
+
"eval_biology_runtime": 49.593,
|
| 839 |
+
"eval_biology_samples_per_second": 10.082,
|
| 840 |
+
"eval_biology_steps_per_second": 2.521,
|
| 841 |
+
"step": 600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.96,
|
| 845 |
+
"eval_chemistry_entropy": 2.062796443462372,
|
| 846 |
+
"eval_chemistry_loss": 2.1318087577819824,
|
| 847 |
+
"eval_chemistry_mean_token_accuracy": 0.6000087871551514,
|
| 848 |
+
"eval_chemistry_num_tokens": 17067407.0,
|
| 849 |
+
"eval_chemistry_runtime": 61.4719,
|
| 850 |
+
"eval_chemistry_samples_per_second": 8.134,
|
| 851 |
+
"eval_chemistry_steps_per_second": 2.033,
|
| 852 |
+
"step": 600
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.96,
|
| 856 |
+
"eval_math_entropy": 0.9119843735694885,
|
| 857 |
+
"eval_math_loss": 0.9157347679138184,
|
| 858 |
+
"eval_math_mean_token_accuracy": 0.7754620661735535,
|
| 859 |
+
"eval_math_num_tokens": 17067407.0,
|
| 860 |
+
"eval_math_runtime": 63.0502,
|
| 861 |
+
"eval_math_samples_per_second": 7.93,
|
| 862 |
+
"eval_math_steps_per_second": 1.983,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.96,
|
| 867 |
+
"eval_physics_entropy": 1.5833718237876893,
|
| 868 |
+
"eval_physics_loss": 1.6547900438308716,
|
| 869 |
+
"eval_physics_mean_token_accuracy": 0.6688490805625915,
|
| 870 |
+
"eval_physics_num_tokens": 17067407.0,
|
| 871 |
+
"eval_physics_runtime": 72.0729,
|
| 872 |
+
"eval_physics_samples_per_second": 6.937,
|
| 873 |
+
"eval_physics_steps_per_second": 1.734,
|
| 874 |
+
"step": 600
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"entropy": 0.8985319763422013,
|
| 878 |
+
"epoch": 0.976,
|
| 879 |
+
"grad_norm": 21.625,
|
| 880 |
+
"learning_rate": 1.7711111111111113e-05,
|
| 881 |
+
"loss": 14.4151,
|
| 882 |
+
"mean_token_accuracy": 0.7804601702839136,
|
| 883 |
+
"num_tokens": 17350994.0,
|
| 884 |
+
"step": 610
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"entropy": 0.9126239087432623,
|
| 888 |
+
"epoch": 0.992,
|
| 889 |
+
"grad_norm": 18.0,
|
| 890 |
+
"learning_rate": 1.763703703703704e-05,
|
| 891 |
+
"loss": 14.6522,
|
| 892 |
+
"mean_token_accuracy": 0.7754363786429167,
|
| 893 |
+
"num_tokens": 17637514.0,
|
| 894 |
+
"step": 620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"entropy": 0.8935651954263448,
|
| 898 |
+
"epoch": 1.008,
|
| 899 |
+
"grad_norm": 17.375,
|
| 900 |
+
"learning_rate": 1.7562962962962962e-05,
|
| 901 |
+
"loss": 14.2584,
|
| 902 |
+
"mean_token_accuracy": 0.7789396952837706,
|
| 903 |
+
"num_tokens": 17926570.0,
|
| 904 |
+
"step": 630
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"entropy": 0.8810664782300591,
|
| 908 |
+
"epoch": 1.024,
|
| 909 |
+
"grad_norm": 17.625,
|
| 910 |
+
"learning_rate": 1.7488888888888892e-05,
|
| 911 |
+
"loss": 14.0978,
|
| 912 |
+
"mean_token_accuracy": 0.7811610117554665,
|
| 913 |
+
"num_tokens": 18207652.0,
|
| 914 |
+
"step": 640
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"entropy": 0.8790556967258454,
|
| 918 |
+
"epoch": 1.04,
|
| 919 |
+
"grad_norm": 20.375,
|
| 920 |
+
"learning_rate": 1.7414814814814815e-05,
|
| 921 |
+
"loss": 14.0815,
|
| 922 |
+
"mean_token_accuracy": 0.782483147084713,
|
| 923 |
+
"num_tokens": 18484931.0,
|
| 924 |
+
"step": 650
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"entropy": 0.872769825719297,
|
| 928 |
+
"epoch": 1.056,
|
| 929 |
+
"grad_norm": 18.625,
|
| 930 |
+
"learning_rate": 1.7340740740740742e-05,
|
| 931 |
+
"loss": 14.2329,
|
| 932 |
+
"mean_token_accuracy": 0.7814408276230097,
|
| 933 |
+
"num_tokens": 18773457.0,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"entropy": 0.8854838136583567,
|
| 938 |
+
"epoch": 1.072,
|
| 939 |
+
"grad_norm": 19.125,
|
| 940 |
+
"learning_rate": 1.726666666666667e-05,
|
| 941 |
+
"loss": 14.1351,
|
| 942 |
+
"mean_token_accuracy": 0.7804106209427119,
|
| 943 |
+
"num_tokens": 19055365.0,
|
| 944 |
+
"step": 670
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"entropy": 0.8737944336608052,
|
| 948 |
+
"epoch": 1.088,
|
| 949 |
+
"grad_norm": 16.625,
|
| 950 |
+
"learning_rate": 1.7192592592592595e-05,
|
| 951 |
+
"loss": 14.0953,
|
| 952 |
+
"mean_token_accuracy": 0.7833730541169643,
|
| 953 |
+
"num_tokens": 19345730.0,
|
| 954 |
+
"step": 680
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"entropy": 0.8823883978649973,
|
| 958 |
+
"epoch": 1.104,
|
| 959 |
+
"grad_norm": 15.1875,
|
| 960 |
+
"learning_rate": 1.711851851851852e-05,
|
| 961 |
+
"loss": 14.1044,
|
| 962 |
+
"mean_token_accuracy": 0.7833204790949821,
|
| 963 |
+
"num_tokens": 19637390.0,
|
| 964 |
+
"step": 690
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"entropy": 0.8538309209048748,
|
| 968 |
+
"epoch": 1.12,
|
| 969 |
+
"grad_norm": 19.5,
|
| 970 |
+
"learning_rate": 1.7044444444444445e-05,
|
| 971 |
+
"loss": 13.6987,
|
| 972 |
+
"mean_token_accuracy": 0.7868878465145827,
|
| 973 |
+
"num_tokens": 19923914.0,
|
| 974 |
+
"step": 700
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.12,
|
| 978 |
+
"eval_biology_entropy": 3.443337703704834,
|
| 979 |
+
"eval_biology_loss": 3.951155662536621,
|
| 980 |
+
"eval_biology_mean_token_accuracy": 0.4163366384506226,
|
| 981 |
+
"eval_biology_num_tokens": 19923914.0,
|
| 982 |
+
"eval_biology_runtime": 49.651,
|
| 983 |
+
"eval_biology_samples_per_second": 10.07,
|
| 984 |
+
"eval_biology_steps_per_second": 2.518,
|
| 985 |
+
"step": 700
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.12,
|
| 989 |
+
"eval_chemistry_entropy": 2.0116386432647704,
|
| 990 |
+
"eval_chemistry_loss": 2.1324052810668945,
|
| 991 |
+
"eval_chemistry_mean_token_accuracy": 0.6028851909637452,
|
| 992 |
+
"eval_chemistry_num_tokens": 19923914.0,
|
| 993 |
+
"eval_chemistry_runtime": 61.5705,
|
| 994 |
+
"eval_chemistry_samples_per_second": 8.121,
|
| 995 |
+
"eval_chemistry_steps_per_second": 2.03,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.12,
|
| 1000 |
+
"eval_math_entropy": 0.8889193925857544,
|
| 1001 |
+
"eval_math_loss": 0.9035109877586365,
|
| 1002 |
+
"eval_math_mean_token_accuracy": 0.7773573837280273,
|
| 1003 |
+
"eval_math_num_tokens": 19923914.0,
|
| 1004 |
+
"eval_math_runtime": 63.1467,
|
| 1005 |
+
"eval_math_samples_per_second": 7.918,
|
| 1006 |
+
"eval_math_steps_per_second": 1.98,
|
| 1007 |
+
"step": 700
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.12,
|
| 1011 |
+
"eval_physics_entropy": 1.5386076803207398,
|
| 1012 |
+
"eval_physics_loss": 1.6331955194473267,
|
| 1013 |
+
"eval_physics_mean_token_accuracy": 0.6719050664901733,
|
| 1014 |
+
"eval_physics_num_tokens": 19923914.0,
|
| 1015 |
+
"eval_physics_runtime": 72.2366,
|
| 1016 |
+
"eval_physics_samples_per_second": 6.922,
|
| 1017 |
+
"eval_physics_steps_per_second": 1.73,
|
| 1018 |
+
"step": 700
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"entropy": 0.8486799146980047,
|
| 1022 |
+
"epoch": 1.1360000000000001,
|
| 1023 |
+
"grad_norm": 18.375,
|
| 1024 |
+
"learning_rate": 1.697037037037037e-05,
|
| 1025 |
+
"loss": 13.6728,
|
| 1026 |
+
"mean_token_accuracy": 0.7864403679966927,
|
| 1027 |
+
"num_tokens": 20201892.0,
|
| 1028 |
+
"step": 710
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"entropy": 0.8742417544126511,
|
| 1032 |
+
"epoch": 1.152,
|
| 1033 |
+
"grad_norm": 20.0,
|
| 1034 |
+
"learning_rate": 1.6896296296296298e-05,
|
| 1035 |
+
"loss": 14.0206,
|
| 1036 |
+
"mean_token_accuracy": 0.7843449763953686,
|
| 1037 |
+
"num_tokens": 20490282.0,
|
| 1038 |
+
"step": 720
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"entropy": 0.8681927429512143,
|
| 1042 |
+
"epoch": 1.168,
|
| 1043 |
+
"grad_norm": 16.625,
|
| 1044 |
+
"learning_rate": 1.6822222222222224e-05,
|
| 1045 |
+
"loss": 13.9888,
|
| 1046 |
+
"mean_token_accuracy": 0.7844074387103319,
|
| 1047 |
+
"num_tokens": 20785786.0,
|
| 1048 |
+
"step": 730
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"entropy": 0.8594187637791038,
|
| 1052 |
+
"epoch": 1.184,
|
| 1053 |
+
"grad_norm": 20.875,
|
| 1054 |
+
"learning_rate": 1.6748148148148147e-05,
|
| 1055 |
+
"loss": 13.8341,
|
| 1056 |
+
"mean_token_accuracy": 0.7861495897173881,
|
| 1057 |
+
"num_tokens": 21074205.0,
|
| 1058 |
+
"step": 740
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"entropy": 0.853638318926096,
|
| 1062 |
+
"epoch": 1.2,
|
| 1063 |
+
"grad_norm": 20.25,
|
| 1064 |
+
"learning_rate": 1.6674074074074077e-05,
|
| 1065 |
+
"loss": 13.7126,
|
| 1066 |
+
"mean_token_accuracy": 0.7865742921829224,
|
| 1067 |
+
"num_tokens": 21369159.0,
|
| 1068 |
+
"step": 750
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"entropy": 0.8770630281418562,
|
| 1072 |
+
"epoch": 1.216,
|
| 1073 |
+
"grad_norm": 23.25,
|
| 1074 |
+
"learning_rate": 1.66e-05,
|
| 1075 |
+
"loss": 14.0894,
|
| 1076 |
+
"mean_token_accuracy": 0.7835288234055042,
|
| 1077 |
+
"num_tokens": 21649178.0,
|
| 1078 |
+
"step": 760
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"entropy": 0.8497887661680579,
|
| 1082 |
+
"epoch": 1.232,
|
| 1083 |
+
"grad_norm": 19.25,
|
| 1084 |
+
"learning_rate": 1.6525925925925927e-05,
|
| 1085 |
+
"loss": 13.5638,
|
| 1086 |
+
"mean_token_accuracy": 0.7882835403084755,
|
| 1087 |
+
"num_tokens": 21930239.0,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"entropy": 0.8405620498582721,
|
| 1092 |
+
"epoch": 1.248,
|
| 1093 |
+
"grad_norm": 17.875,
|
| 1094 |
+
"learning_rate": 1.6451851851851853e-05,
|
| 1095 |
+
"loss": 13.5058,
|
| 1096 |
+
"mean_token_accuracy": 0.7887706879526377,
|
| 1097 |
+
"num_tokens": 22216387.0,
|
| 1098 |
+
"step": 780
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"entropy": 0.8788484372198582,
|
| 1102 |
+
"epoch": 1.264,
|
| 1103 |
+
"grad_norm": 20.125,
|
| 1104 |
+
"learning_rate": 1.637777777777778e-05,
|
| 1105 |
+
"loss": 14.209,
|
| 1106 |
+
"mean_token_accuracy": 0.7804543025791645,
|
| 1107 |
+
"num_tokens": 22501002.0,
|
| 1108 |
+
"step": 790
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"entropy": 0.8771140918135643,
|
| 1112 |
+
"epoch": 1.28,
|
| 1113 |
+
"grad_norm": 22.25,
|
| 1114 |
+
"learning_rate": 1.6303703703703706e-05,
|
| 1115 |
+
"loss": 13.9869,
|
| 1116 |
+
"mean_token_accuracy": 0.7842618364840745,
|
| 1117 |
+
"num_tokens": 22779682.0,
|
| 1118 |
+
"step": 800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.28,
|
| 1122 |
+
"eval_biology_entropy": 3.436663423538208,
|
| 1123 |
+
"eval_biology_loss": 3.9039478302001953,
|
| 1124 |
+
"eval_biology_mean_token_accuracy": 0.41795943784713746,
|
| 1125 |
+
"eval_biology_num_tokens": 22779682.0,
|
| 1126 |
+
"eval_biology_runtime": 49.6843,
|
| 1127 |
+
"eval_biology_samples_per_second": 10.064,
|
| 1128 |
+
"eval_biology_steps_per_second": 2.516,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.28,
|
| 1133 |
+
"eval_chemistry_entropy": 1.97736017036438,
|
| 1134 |
+
"eval_chemistry_loss": 2.080076217651367,
|
| 1135 |
+
"eval_chemistry_mean_token_accuracy": 0.606924372434616,
|
| 1136 |
+
"eval_chemistry_num_tokens": 22779682.0,
|
| 1137 |
+
"eval_chemistry_runtime": 61.5504,
|
| 1138 |
+
"eval_chemistry_samples_per_second": 8.123,
|
| 1139 |
+
"eval_chemistry_steps_per_second": 2.031,
|
| 1140 |
+
"step": 800
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.28,
|
| 1144 |
+
"eval_math_entropy": 0.8625033555030823,
|
| 1145 |
+
"eval_math_loss": 0.892142653465271,
|
| 1146 |
+
"eval_math_mean_token_accuracy": 0.7796395468711853,
|
| 1147 |
+
"eval_math_num_tokens": 22779682.0,
|
| 1148 |
+
"eval_math_runtime": 63.1583,
|
| 1149 |
+
"eval_math_samples_per_second": 7.917,
|
| 1150 |
+
"eval_math_steps_per_second": 1.979,
|
| 1151 |
+
"step": 800
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.28,
|
| 1155 |
+
"eval_physics_entropy": 1.5225397615432739,
|
| 1156 |
+
"eval_physics_loss": 1.612709879875183,
|
| 1157 |
+
"eval_physics_mean_token_accuracy": 0.674011738061905,
|
| 1158 |
+
"eval_physics_num_tokens": 22779682.0,
|
| 1159 |
+
"eval_physics_runtime": 72.1546,
|
| 1160 |
+
"eval_physics_samples_per_second": 6.93,
|
| 1161 |
+
"eval_physics_steps_per_second": 1.732,
|
| 1162 |
+
"step": 800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"entropy": 0.8474511569365859,
|
| 1166 |
+
"epoch": 1.296,
|
| 1167 |
+
"grad_norm": 17.75,
|
| 1168 |
+
"learning_rate": 1.622962962962963e-05,
|
| 1169 |
+
"loss": 13.6822,
|
| 1170 |
+
"mean_token_accuracy": 0.7866408120840788,
|
| 1171 |
+
"num_tokens": 23057744.0,
|
| 1172 |
+
"step": 810
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"entropy": 0.8580924984067678,
|
| 1176 |
+
"epoch": 1.312,
|
| 1177 |
+
"grad_norm": 21.5,
|
| 1178 |
+
"learning_rate": 1.6155555555555556e-05,
|
| 1179 |
+
"loss": 13.9676,
|
| 1180 |
+
"mean_token_accuracy": 0.7842281598597765,
|
| 1181 |
+
"num_tokens": 23344644.0,
|
| 1182 |
+
"step": 820
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"entropy": 0.8850870780646801,
|
| 1186 |
+
"epoch": 1.328,
|
| 1187 |
+
"grad_norm": 21.5,
|
| 1188 |
+
"learning_rate": 1.6081481481481482e-05,
|
| 1189 |
+
"loss": 14.0615,
|
| 1190 |
+
"mean_token_accuracy": 0.781786335259676,
|
| 1191 |
+
"num_tokens": 23622405.0,
|
| 1192 |
+
"step": 830
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"entropy": 0.8474001951515675,
|
| 1196 |
+
"epoch": 1.3439999999999999,
|
| 1197 |
+
"grad_norm": 18.25,
|
| 1198 |
+
"learning_rate": 1.600740740740741e-05,
|
| 1199 |
+
"loss": 13.6058,
|
| 1200 |
+
"mean_token_accuracy": 0.7873330093920231,
|
| 1201 |
+
"num_tokens": 23899771.0,
|
| 1202 |
+
"step": 840
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"entropy": 0.8435361562296748,
|
| 1206 |
+
"epoch": 1.3599999999999999,
|
| 1207 |
+
"grad_norm": 16.0,
|
| 1208 |
+
"learning_rate": 1.5933333333333336e-05,
|
| 1209 |
+
"loss": 13.6319,
|
| 1210 |
+
"mean_token_accuracy": 0.7882646590471267,
|
| 1211 |
+
"num_tokens": 24187023.0,
|
| 1212 |
+
"step": 850
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"entropy": 0.9156765401363373,
|
| 1216 |
+
"epoch": 1.376,
|
| 1217 |
+
"grad_norm": 21.5,
|
| 1218 |
+
"learning_rate": 1.5859259259259262e-05,
|
| 1219 |
+
"loss": 14.6843,
|
| 1220 |
+
"mean_token_accuracy": 0.7743376530706882,
|
| 1221 |
+
"num_tokens": 24466132.0,
|
| 1222 |
+
"step": 860
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"entropy": 0.8523435527458787,
|
| 1226 |
+
"epoch": 1.392,
|
| 1227 |
+
"grad_norm": 20.75,
|
| 1228 |
+
"learning_rate": 1.5785185185185185e-05,
|
| 1229 |
+
"loss": 13.6998,
|
| 1230 |
+
"mean_token_accuracy": 0.7863496944308281,
|
| 1231 |
+
"num_tokens": 24748043.0,
|
| 1232 |
+
"step": 870
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"entropy": 0.8375731509178876,
|
| 1236 |
+
"epoch": 1.408,
|
| 1237 |
+
"grad_norm": 21.125,
|
| 1238 |
+
"learning_rate": 1.571111111111111e-05,
|
| 1239 |
+
"loss": 13.5188,
|
| 1240 |
+
"mean_token_accuracy": 0.7898116644471884,
|
| 1241 |
+
"num_tokens": 25036674.0,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"entropy": 0.8376417780295015,
|
| 1246 |
+
"epoch": 1.424,
|
| 1247 |
+
"grad_norm": 15.25,
|
| 1248 |
+
"learning_rate": 1.5637037037037038e-05,
|
| 1249 |
+
"loss": 13.4567,
|
| 1250 |
+
"mean_token_accuracy": 0.7908716473728419,
|
| 1251 |
+
"num_tokens": 25324579.0,
|
| 1252 |
+
"step": 890
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"entropy": 0.8603908697143197,
|
| 1256 |
+
"epoch": 1.44,
|
| 1257 |
+
"grad_norm": 19.125,
|
| 1258 |
+
"learning_rate": 1.5562962962962965e-05,
|
| 1259 |
+
"loss": 13.9612,
|
| 1260 |
+
"mean_token_accuracy": 0.7841609816998243,
|
| 1261 |
+
"num_tokens": 25606824.0,
|
| 1262 |
+
"step": 900
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.44,
|
| 1266 |
+
"eval_biology_entropy": 3.45110001373291,
|
| 1267 |
+
"eval_biology_loss": 3.8754560947418213,
|
| 1268 |
+
"eval_biology_mean_token_accuracy": 0.4207558875083923,
|
| 1269 |
+
"eval_biology_num_tokens": 25606824.0,
|
| 1270 |
+
"eval_biology_runtime": 49.6588,
|
| 1271 |
+
"eval_biology_samples_per_second": 10.069,
|
| 1272 |
+
"eval_biology_steps_per_second": 2.517,
|
| 1273 |
+
"step": 900
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.44,
|
| 1277 |
+
"eval_chemistry_entropy": 1.9984806547164917,
|
| 1278 |
+
"eval_chemistry_loss": 2.088613748550415,
|
| 1279 |
+
"eval_chemistry_mean_token_accuracy": 0.607667599439621,
|
| 1280 |
+
"eval_chemistry_num_tokens": 25606824.0,
|
| 1281 |
+
"eval_chemistry_runtime": 61.604,
|
| 1282 |
+
"eval_chemistry_samples_per_second": 8.116,
|
| 1283 |
+
"eval_chemistry_steps_per_second": 2.029,
|
| 1284 |
+
"step": 900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.44,
|
| 1288 |
+
"eval_math_entropy": 0.8740571973323822,
|
| 1289 |
+
"eval_math_loss": 0.8836535811424255,
|
| 1290 |
+
"eval_math_mean_token_accuracy": 0.7810649185180664,
|
| 1291 |
+
"eval_math_num_tokens": 25606824.0,
|
| 1292 |
+
"eval_math_runtime": 63.1568,
|
| 1293 |
+
"eval_math_samples_per_second": 7.917,
|
| 1294 |
+
"eval_math_steps_per_second": 1.979,
|
| 1295 |
+
"step": 900
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.44,
|
| 1299 |
+
"eval_physics_entropy": 1.533125587463379,
|
| 1300 |
+
"eval_physics_loss": 1.6004778146743774,
|
| 1301 |
+
"eval_physics_mean_token_accuracy": 0.6762587761878968,
|
| 1302 |
+
"eval_physics_num_tokens": 25606824.0,
|
| 1303 |
+
"eval_physics_runtime": 71.9331,
|
| 1304 |
+
"eval_physics_samples_per_second": 6.951,
|
| 1305 |
+
"eval_physics_steps_per_second": 1.738,
|
| 1306 |
+
"step": 900
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"entropy": 0.8511543165892362,
|
| 1310 |
+
"epoch": 1.456,
|
| 1311 |
+
"grad_norm": 16.125,
|
| 1312 |
+
"learning_rate": 1.548888888888889e-05,
|
| 1313 |
+
"loss": 13.5133,
|
| 1314 |
+
"mean_token_accuracy": 0.7876119159162045,
|
| 1315 |
+
"num_tokens": 25886396.0,
|
| 1316 |
+
"step": 910
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"entropy": 0.8463271845132112,
|
| 1320 |
+
"epoch": 1.472,
|
| 1321 |
+
"grad_norm": 17.75,
|
| 1322 |
+
"learning_rate": 1.5414814814814814e-05,
|
| 1323 |
+
"loss": 13.5862,
|
| 1324 |
+
"mean_token_accuracy": 0.787867683917284,
|
| 1325 |
+
"num_tokens": 26163618.0,
|
| 1326 |
+
"step": 920
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"entropy": 0.8713837819173932,
|
| 1330 |
+
"epoch": 1.488,
|
| 1331 |
+
"grad_norm": 20.125,
|
| 1332 |
+
"learning_rate": 1.5340740740740744e-05,
|
| 1333 |
+
"loss": 14.1889,
|
| 1334 |
+
"mean_token_accuracy": 0.7813853111118079,
|
| 1335 |
+
"num_tokens": 26438338.0,
|
| 1336 |
+
"step": 930
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"entropy": 0.834681292809546,
|
| 1340 |
+
"epoch": 1.504,
|
| 1341 |
+
"grad_norm": 21.875,
|
| 1342 |
+
"learning_rate": 1.5266666666666667e-05,
|
| 1343 |
+
"loss": 13.4447,
|
| 1344 |
+
"mean_token_accuracy": 0.7905492588877678,
|
| 1345 |
+
"num_tokens": 26729255.0,
|
| 1346 |
+
"step": 940
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"entropy": 0.8771929260343313,
|
| 1350 |
+
"epoch": 1.52,
|
| 1351 |
+
"grad_norm": 18.0,
|
| 1352 |
+
"learning_rate": 1.5192592592592594e-05,
|
| 1353 |
+
"loss": 14.0064,
|
| 1354 |
+
"mean_token_accuracy": 0.7831294402480126,
|
| 1355 |
+
"num_tokens": 27017935.0,
|
| 1356 |
+
"step": 950
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"entropy": 0.8460531679913401,
|
| 1360 |
+
"epoch": 1.536,
|
| 1361 |
+
"grad_norm": 16.125,
|
| 1362 |
+
"learning_rate": 1.5118518518518519e-05,
|
| 1363 |
+
"loss": 13.6594,
|
| 1364 |
+
"mean_token_accuracy": 0.786826192215085,
|
| 1365 |
+
"num_tokens": 27306339.0,
|
| 1366 |
+
"step": 960
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"entropy": 0.8540312614291906,
|
| 1370 |
+
"epoch": 1.552,
|
| 1371 |
+
"grad_norm": 18.75,
|
| 1372 |
+
"learning_rate": 1.5044444444444445e-05,
|
| 1373 |
+
"loss": 13.6638,
|
| 1374 |
+
"mean_token_accuracy": 0.7870731830596924,
|
| 1375 |
+
"num_tokens": 27591959.0,
|
| 1376 |
+
"step": 970
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"entropy": 0.8264467475935817,
|
| 1380 |
+
"epoch": 1.568,
|
| 1381 |
+
"grad_norm": 16.125,
|
| 1382 |
+
"learning_rate": 1.497037037037037e-05,
|
| 1383 |
+
"loss": 13.3238,
|
| 1384 |
+
"mean_token_accuracy": 0.7920118164271116,
|
| 1385 |
+
"num_tokens": 27884398.0,
|
| 1386 |
+
"step": 980
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"entropy": 0.8386921418830753,
|
| 1390 |
+
"epoch": 1.584,
|
| 1391 |
+
"grad_norm": 20.25,
|
| 1392 |
+
"learning_rate": 1.4896296296296298e-05,
|
| 1393 |
+
"loss": 13.5938,
|
| 1394 |
+
"mean_token_accuracy": 0.7884967364370823,
|
| 1395 |
+
"num_tokens": 28171274.0,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"entropy": 0.8454421229660511,
|
| 1400 |
+
"epoch": 1.6,
|
| 1401 |
+
"grad_norm": 21.125,
|
| 1402 |
+
"learning_rate": 1.4822222222222225e-05,
|
| 1403 |
+
"loss": 13.4115,
|
| 1404 |
+
"mean_token_accuracy": 0.7884562328457833,
|
| 1405 |
+
"num_tokens": 28457624.0,
|
| 1406 |
+
"step": 1000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.6,
|
| 1410 |
+
"eval_biology_entropy": 3.4279630908966063,
|
| 1411 |
+
"eval_biology_loss": 3.9252524375915527,
|
| 1412 |
+
"eval_biology_mean_token_accuracy": 0.42100021028518675,
|
| 1413 |
+
"eval_biology_num_tokens": 28457624.0,
|
| 1414 |
+
"eval_biology_runtime": 49.5484,
|
| 1415 |
+
"eval_biology_samples_per_second": 10.091,
|
| 1416 |
+
"eval_biology_steps_per_second": 2.523,
|
| 1417 |
+
"step": 1000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.6,
|
| 1421 |
+
"eval_chemistry_entropy": 1.9675587797164917,
|
| 1422 |
+
"eval_chemistry_loss": 2.0829849243164062,
|
| 1423 |
+
"eval_chemistry_mean_token_accuracy": 0.6087198803424835,
|
| 1424 |
+
"eval_chemistry_num_tokens": 28457624.0,
|
| 1425 |
+
"eval_chemistry_runtime": 60.8881,
|
| 1426 |
+
"eval_chemistry_samples_per_second": 8.212,
|
| 1427 |
+
"eval_chemistry_steps_per_second": 2.053,
|
| 1428 |
+
"step": 1000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.6,
|
| 1432 |
+
"eval_math_entropy": 0.858300416469574,
|
| 1433 |
+
"eval_math_loss": 0.8771592974662781,
|
| 1434 |
+
"eval_math_mean_token_accuracy": 0.7824492840766907,
|
| 1435 |
+
"eval_math_num_tokens": 28457624.0,
|
| 1436 |
+
"eval_math_runtime": 62.7471,
|
| 1437 |
+
"eval_math_samples_per_second": 7.968,
|
| 1438 |
+
"eval_math_steps_per_second": 1.992,
|
| 1439 |
+
"step": 1000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.6,
|
| 1443 |
+
"eval_physics_entropy": 1.5079545302391053,
|
| 1444 |
+
"eval_physics_loss": 1.5952943563461304,
|
| 1445 |
+
"eval_physics_mean_token_accuracy": 0.6772087650299072,
|
| 1446 |
+
"eval_physics_num_tokens": 28457624.0,
|
| 1447 |
+
"eval_physics_runtime": 71.6735,
|
| 1448 |
+
"eval_physics_samples_per_second": 6.976,
|
| 1449 |
+
"eval_physics_steps_per_second": 1.744,
|
| 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": 2.897870312538204e+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:d1c008157b73be070634bdb117a0dc9153ffef3e4614d97e241f79e0382d3afe
|
| 3 |
+
size 6417
|