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 sha256:09d1e04dc9e5b0e235ee60dbc70671dac95cf04553e5ccb871e944cb3e712ae2
|
| 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 sha256:5809826c2cf020ca422d580fddb62817fa666afd074213543d80559ba858c7a0
|
| 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": 0.9036113740876317,
|
| 14 |
+
"epoch": 0.016,
|
| 15 |
+
"grad_norm": 128.0,
|
| 16 |
+
"learning_rate": 6.000000000000001e-07,
|
| 17 |
+
"loss": 34.907,
|
| 18 |
+
"mean_token_accuracy": 0.6652832090854645,
|
| 19 |
+
"num_tokens": 338352.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.9087308555841446,
|
| 24 |
+
"epoch": 0.032,
|
| 25 |
+
"grad_norm": 119.5,
|
| 26 |
+
"learning_rate": 1.2666666666666669e-06,
|
| 27 |
+
"loss": 34.745,
|
| 28 |
+
"mean_token_accuracy": 0.6691140927374363,
|
| 29 |
+
"num_tokens": 671193.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.9059555266052485,
|
| 34 |
+
"epoch": 0.048,
|
| 35 |
+
"grad_norm": 109.5,
|
| 36 |
+
"learning_rate": 1.9333333333333336e-06,
|
| 37 |
+
"loss": 34.1928,
|
| 38 |
+
"mean_token_accuracy": 0.6685802672058344,
|
| 39 |
+
"num_tokens": 1001008.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.9450886320322752,
|
| 44 |
+
"epoch": 0.064,
|
| 45 |
+
"grad_norm": 102.0,
|
| 46 |
+
"learning_rate": 2.6e-06,
|
| 47 |
+
"loss": 34.8515,
|
| 48 |
+
"mean_token_accuracy": 0.6614982625469565,
|
| 49 |
+
"num_tokens": 1331208.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.9593638770282269,
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"grad_norm": 94.5,
|
| 56 |
+
"learning_rate": 3.266666666666667e-06,
|
| 57 |
+
"loss": 33.1046,
|
| 58 |
+
"mean_token_accuracy": 0.6680185409262777,
|
| 59 |
+
"num_tokens": 1667532.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.9606023650616408,
|
| 64 |
+
"epoch": 0.096,
|
| 65 |
+
"grad_norm": 80.0,
|
| 66 |
+
"learning_rate": 3.9333333333333335e-06,
|
| 67 |
+
"loss": 31.2876,
|
| 68 |
+
"mean_token_accuracy": 0.678196857497096,
|
| 69 |
+
"num_tokens": 2007176.0,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.069316839799285,
|
| 74 |
+
"epoch": 0.112,
|
| 75 |
+
"grad_norm": 63.25,
|
| 76 |
+
"learning_rate": 4.600000000000001e-06,
|
| 77 |
+
"loss": 30.7512,
|
| 78 |
+
"mean_token_accuracy": 0.6743977405130863,
|
| 79 |
+
"num_tokens": 2342259.0,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 1.2628379821777345,
|
| 84 |
+
"epoch": 0.128,
|
| 85 |
+
"grad_norm": 48.0,
|
| 86 |
+
"learning_rate": 5.2666666666666665e-06,
|
| 87 |
+
"loss": 30.3935,
|
| 88 |
+
"mean_token_accuracy": 0.6708028431981802,
|
| 89 |
+
"num_tokens": 2663987.0,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.3055987607687711,
|
| 94 |
+
"epoch": 0.144,
|
| 95 |
+
"grad_norm": 32.25,
|
| 96 |
+
"learning_rate": 5.933333333333335e-06,
|
| 97 |
+
"loss": 27.3167,
|
| 98 |
+
"mean_token_accuracy": 0.6920903529971838,
|
| 99 |
+
"num_tokens": 2997824.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.3579398691654205,
|
| 104 |
+
"epoch": 0.16,
|
| 105 |
+
"grad_norm": 24.625,
|
| 106 |
+
"learning_rate": 6.600000000000001e-06,
|
| 107 |
+
"loss": 25.5362,
|
| 108 |
+
"mean_token_accuracy": 0.7021430663764476,
|
| 109 |
+
"num_tokens": 3330597.0,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.16,
|
| 114 |
+
"eval_biology_entropy": 3.549320913314819,
|
| 115 |
+
"eval_biology_loss": 4.242035388946533,
|
| 116 |
+
"eval_biology_mean_token_accuracy": 0.4143077299594879,
|
| 117 |
+
"eval_biology_num_tokens": 3330597.0,
|
| 118 |
+
"eval_biology_runtime": 55.9019,
|
| 119 |
+
"eval_biology_samples_per_second": 8.944,
|
| 120 |
+
"eval_biology_steps_per_second": 2.236,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.16,
|
| 125 |
+
"eval_chemistry_entropy": 1.9644288024902343,
|
| 126 |
+
"eval_chemistry_loss": 2.1523141860961914,
|
| 127 |
+
"eval_chemistry_mean_token_accuracy": 0.635781112909317,
|
| 128 |
+
"eval_chemistry_num_tokens": 3330597.0,
|
| 129 |
+
"eval_chemistry_runtime": 69.6126,
|
| 130 |
+
"eval_chemistry_samples_per_second": 7.183,
|
| 131 |
+
"eval_chemistry_steps_per_second": 1.796,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.16,
|
| 136 |
+
"eval_math_entropy": 1.1708643288612366,
|
| 137 |
+
"eval_math_loss": 1.6400102376937866,
|
| 138 |
+
"eval_math_mean_token_accuracy": 0.7028316712379455,
|
| 139 |
+
"eval_math_num_tokens": 3330597.0,
|
| 140 |
+
"eval_math_runtime": 71.6855,
|
| 141 |
+
"eval_math_samples_per_second": 6.975,
|
| 142 |
+
"eval_math_steps_per_second": 1.744,
|
| 143 |
+
"step": 100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.16,
|
| 147 |
+
"eval_physics_entropy": 1.388730420589447,
|
| 148 |
+
"eval_physics_loss": 1.5701876878738403,
|
| 149 |
+
"eval_physics_mean_token_accuracy": 0.7025446329116821,
|
| 150 |
+
"eval_physics_num_tokens": 3330597.0,
|
| 151 |
+
"eval_physics_runtime": 83.1014,
|
| 152 |
+
"eval_physics_samples_per_second": 6.017,
|
| 153 |
+
"eval_physics_steps_per_second": 1.504,
|
| 154 |
+
"step": 100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"entropy": 1.3951868526637554,
|
| 158 |
+
"epoch": 0.176,
|
| 159 |
+
"grad_norm": 23.0,
|
| 160 |
+
"learning_rate": 7.266666666666668e-06,
|
| 161 |
+
"loss": 24.797,
|
| 162 |
+
"mean_token_accuracy": 0.7061628632247448,
|
| 163 |
+
"num_tokens": 3658264.0,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"entropy": 1.3387951213866471,
|
| 168 |
+
"epoch": 0.192,
|
| 169 |
+
"grad_norm": 15.375,
|
| 170 |
+
"learning_rate": 7.933333333333334e-06,
|
| 171 |
+
"loss": 23.7842,
|
| 172 |
+
"mean_token_accuracy": 0.713041927665472,
|
| 173 |
+
"num_tokens": 3995568.0,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"entropy": 1.3034498687833547,
|
| 178 |
+
"epoch": 0.208,
|
| 179 |
+
"grad_norm": 17.5,
|
| 180 |
+
"learning_rate": 8.6e-06,
|
| 181 |
+
"loss": 22.4839,
|
| 182 |
+
"mean_token_accuracy": 0.7252091735601425,
|
| 183 |
+
"num_tokens": 4321436.0,
|
| 184 |
+
"step": 130
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"entropy": 1.2866257604211568,
|
| 188 |
+
"epoch": 0.224,
|
| 189 |
+
"grad_norm": 14.6875,
|
| 190 |
+
"learning_rate": 9.266666666666667e-06,
|
| 191 |
+
"loss": 22.0837,
|
| 192 |
+
"mean_token_accuracy": 0.7270880017429591,
|
| 193 |
+
"num_tokens": 4648491.0,
|
| 194 |
+
"step": 140
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"entropy": 1.268964756652713,
|
| 198 |
+
"epoch": 0.24,
|
| 199 |
+
"grad_norm": 14.25,
|
| 200 |
+
"learning_rate": 9.933333333333334e-06,
|
| 201 |
+
"loss": 21.6129,
|
| 202 |
+
"mean_token_accuracy": 0.7301765695214272,
|
| 203 |
+
"num_tokens": 4986175.0,
|
| 204 |
+
"step": 150
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"entropy": 1.2642716094851494,
|
| 208 |
+
"epoch": 0.256,
|
| 209 |
+
"grad_norm": 15.5625,
|
| 210 |
+
"learning_rate": 1.0600000000000002e-05,
|
| 211 |
+
"loss": 21.2618,
|
| 212 |
+
"mean_token_accuracy": 0.734415826946497,
|
| 213 |
+
"num_tokens": 5329320.0,
|
| 214 |
+
"step": 160
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"entropy": 1.2717196103185415,
|
| 218 |
+
"epoch": 0.272,
|
| 219 |
+
"grad_norm": 17.5,
|
| 220 |
+
"learning_rate": 1.1266666666666668e-05,
|
| 221 |
+
"loss": 21.4982,
|
| 222 |
+
"mean_token_accuracy": 0.7297716859728098,
|
| 223 |
+
"num_tokens": 5658796.0,
|
| 224 |
+
"step": 170
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"entropy": 1.2510493908077478,
|
| 228 |
+
"epoch": 0.288,
|
| 229 |
+
"grad_norm": 14.5625,
|
| 230 |
+
"learning_rate": 1.1933333333333335e-05,
|
| 231 |
+
"loss": 21.0954,
|
| 232 |
+
"mean_token_accuracy": 0.7358391582965851,
|
| 233 |
+
"num_tokens": 5980201.0,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"entropy": 1.2463122855871915,
|
| 238 |
+
"epoch": 0.304,
|
| 239 |
+
"grad_norm": 19.5,
|
| 240 |
+
"learning_rate": 1.2600000000000001e-05,
|
| 241 |
+
"loss": 20.8303,
|
| 242 |
+
"mean_token_accuracy": 0.7361553307622671,
|
| 243 |
+
"num_tokens": 6298858.0,
|
| 244 |
+
"step": 190
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"entropy": 1.215079977735877,
|
| 248 |
+
"epoch": 0.32,
|
| 249 |
+
"grad_norm": 15.875,
|
| 250 |
+
"learning_rate": 1.3266666666666668e-05,
|
| 251 |
+
"loss": 20.4326,
|
| 252 |
+
"mean_token_accuracy": 0.7394854992628097,
|
| 253 |
+
"num_tokens": 6622798.0,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.32,
|
| 258 |
+
"eval_biology_entropy": 3.1598935775756836,
|
| 259 |
+
"eval_biology_loss": 3.6490557193756104,
|
| 260 |
+
"eval_biology_mean_token_accuracy": 0.45875698828697203,
|
| 261 |
+
"eval_biology_num_tokens": 6622798.0,
|
| 262 |
+
"eval_biology_runtime": 56.3027,
|
| 263 |
+
"eval_biology_samples_per_second": 8.881,
|
| 264 |
+
"eval_biology_steps_per_second": 2.22,
|
| 265 |
+
"step": 200
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.32,
|
| 269 |
+
"eval_chemistry_entropy": 1.6644244351387023,
|
| 270 |
+
"eval_chemistry_loss": 1.768973469734192,
|
| 271 |
+
"eval_chemistry_mean_token_accuracy": 0.6738141541481018,
|
| 272 |
+
"eval_chemistry_num_tokens": 6622798.0,
|
| 273 |
+
"eval_chemistry_runtime": 69.6913,
|
| 274 |
+
"eval_chemistry_samples_per_second": 7.174,
|
| 275 |
+
"eval_chemistry_steps_per_second": 1.794,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.32,
|
| 280 |
+
"eval_math_entropy": 1.124363118648529,
|
| 281 |
+
"eval_math_loss": 1.4134961366653442,
|
| 282 |
+
"eval_math_mean_token_accuracy": 0.7205373592376709,
|
| 283 |
+
"eval_math_num_tokens": 6622798.0,
|
| 284 |
+
"eval_math_runtime": 71.6804,
|
| 285 |
+
"eval_math_samples_per_second": 6.975,
|
| 286 |
+
"eval_math_steps_per_second": 1.744,
|
| 287 |
+
"step": 200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.32,
|
| 291 |
+
"eval_physics_entropy": 1.2113610072135925,
|
| 292 |
+
"eval_physics_loss": 1.2715808153152466,
|
| 293 |
+
"eval_physics_mean_token_accuracy": 0.7393231744766235,
|
| 294 |
+
"eval_physics_num_tokens": 6622798.0,
|
| 295 |
+
"eval_physics_runtime": 83.0035,
|
| 296 |
+
"eval_physics_samples_per_second": 6.024,
|
| 297 |
+
"eval_physics_steps_per_second": 1.506,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"entropy": 1.2057966101914643,
|
| 302 |
+
"epoch": 0.336,
|
| 303 |
+
"grad_norm": 13.875,
|
| 304 |
+
"learning_rate": 1.3933333333333334e-05,
|
| 305 |
+
"loss": 20.1637,
|
| 306 |
+
"mean_token_accuracy": 0.740947175398469,
|
| 307 |
+
"num_tokens": 6953611.0,
|
| 308 |
+
"step": 210
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"entropy": 1.1682135988026858,
|
| 312 |
+
"epoch": 0.352,
|
| 313 |
+
"grad_norm": 14.625,
|
| 314 |
+
"learning_rate": 1.46e-05,
|
| 315 |
+
"loss": 19.5323,
|
| 316 |
+
"mean_token_accuracy": 0.748641949146986,
|
| 317 |
+
"num_tokens": 7290378.0,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"entropy": 1.1533767595887183,
|
| 322 |
+
"epoch": 0.368,
|
| 323 |
+
"grad_norm": 14.75,
|
| 324 |
+
"learning_rate": 1.5266666666666667e-05,
|
| 325 |
+
"loss": 19.3393,
|
| 326 |
+
"mean_token_accuracy": 0.7496714886277914,
|
| 327 |
+
"num_tokens": 7621082.0,
|
| 328 |
+
"step": 230
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"entropy": 1.2154120814055205,
|
| 332 |
+
"epoch": 0.384,
|
| 333 |
+
"grad_norm": 13.875,
|
| 334 |
+
"learning_rate": 1.5933333333333336e-05,
|
| 335 |
+
"loss": 20.1519,
|
| 336 |
+
"mean_token_accuracy": 0.7383838955312967,
|
| 337 |
+
"num_tokens": 7955570.0,
|
| 338 |
+
"step": 240
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"entropy": 1.162219974398613,
|
| 342 |
+
"epoch": 0.4,
|
| 343 |
+
"grad_norm": 17.0,
|
| 344 |
+
"learning_rate": 1.66e-05,
|
| 345 |
+
"loss": 19.3544,
|
| 346 |
+
"mean_token_accuracy": 0.7475786007940769,
|
| 347 |
+
"num_tokens": 8291049.0,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"entropy": 1.1398306384682655,
|
| 352 |
+
"epoch": 0.416,
|
| 353 |
+
"grad_norm": 17.0,
|
| 354 |
+
"learning_rate": 1.726666666666667e-05,
|
| 355 |
+
"loss": 18.9335,
|
| 356 |
+
"mean_token_accuracy": 0.7522856764495373,
|
| 357 |
+
"num_tokens": 8627310.0,
|
| 358 |
+
"step": 260
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"entropy": 1.160587527230382,
|
| 362 |
+
"epoch": 0.432,
|
| 363 |
+
"grad_norm": 14.5,
|
| 364 |
+
"learning_rate": 1.7933333333333333e-05,
|
| 365 |
+
"loss": 19.2248,
|
| 366 |
+
"mean_token_accuracy": 0.7491097755730152,
|
| 367 |
+
"num_tokens": 8958371.0,
|
| 368 |
+
"step": 270
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"entropy": 1.1003841817378999,
|
| 372 |
+
"epoch": 0.448,
|
| 373 |
+
"grad_norm": 14.0,
|
| 374 |
+
"learning_rate": 1.86e-05,
|
| 375 |
+
"loss": 18.3143,
|
| 376 |
+
"mean_token_accuracy": 0.7592806451022625,
|
| 377 |
+
"num_tokens": 9294388.0,
|
| 378 |
+
"step": 280
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"entropy": 1.1066032487899065,
|
| 382 |
+
"epoch": 0.464,
|
| 383 |
+
"grad_norm": 15.375,
|
| 384 |
+
"learning_rate": 1.926666666666667e-05,
|
| 385 |
+
"loss": 18.3092,
|
| 386 |
+
"mean_token_accuracy": 0.7574895836412907,
|
| 387 |
+
"num_tokens": 9620366.0,
|
| 388 |
+
"step": 290
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"entropy": 1.1134729530662297,
|
| 392 |
+
"epoch": 0.48,
|
| 393 |
+
"grad_norm": 14.875,
|
| 394 |
+
"learning_rate": 1.9933333333333334e-05,
|
| 395 |
+
"loss": 18.5931,
|
| 396 |
+
"mean_token_accuracy": 0.7540634006261826,
|
| 397 |
+
"num_tokens": 9955431.0,
|
| 398 |
+
"step": 300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.48,
|
| 402 |
+
"eval_biology_entropy": 3.058082123756409,
|
| 403 |
+
"eval_biology_loss": 3.4944381713867188,
|
| 404 |
+
"eval_biology_mean_token_accuracy": 0.4677197203636169,
|
| 405 |
+
"eval_biology_num_tokens": 9955431.0,
|
| 406 |
+
"eval_biology_runtime": 56.129,
|
| 407 |
+
"eval_biology_samples_per_second": 8.908,
|
| 408 |
+
"eval_biology_steps_per_second": 2.227,
|
| 409 |
+
"step": 300
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.48,
|
| 413 |
+
"eval_chemistry_entropy": 1.584096737384796,
|
| 414 |
+
"eval_chemistry_loss": 1.6560814380645752,
|
| 415 |
+
"eval_chemistry_mean_token_accuracy": 0.6847201838493348,
|
| 416 |
+
"eval_chemistry_num_tokens": 9955431.0,
|
| 417 |
+
"eval_chemistry_runtime": 69.5947,
|
| 418 |
+
"eval_chemistry_samples_per_second": 7.184,
|
| 419 |
+
"eval_chemistry_steps_per_second": 1.796,
|
| 420 |
+
"step": 300
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.48,
|
| 424 |
+
"eval_math_entropy": 1.1037719421386718,
|
| 425 |
+
"eval_math_loss": 1.3507343530654907,
|
| 426 |
+
"eval_math_mean_token_accuracy": 0.7274009571075439,
|
| 427 |
+
"eval_math_num_tokens": 9955431.0,
|
| 428 |
+
"eval_math_runtime": 71.8212,
|
| 429 |
+
"eval_math_samples_per_second": 6.962,
|
| 430 |
+
"eval_math_steps_per_second": 1.74,
|
| 431 |
+
"step": 300
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.48,
|
| 435 |
+
"eval_physics_entropy": 1.1398421788215638,
|
| 436 |
+
"eval_physics_loss": 1.1733136177062988,
|
| 437 |
+
"eval_physics_mean_token_accuracy": 0.7520353999137879,
|
| 438 |
+
"eval_physics_num_tokens": 9955431.0,
|
| 439 |
+
"eval_physics_runtime": 83.0575,
|
| 440 |
+
"eval_physics_samples_per_second": 6.02,
|
| 441 |
+
"eval_physics_steps_per_second": 1.505,
|
| 442 |
+
"step": 300
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"entropy": 1.1404459465295076,
|
| 446 |
+
"epoch": 0.496,
|
| 447 |
+
"grad_norm": 14.25,
|
| 448 |
+
"learning_rate": 1.9933333333333334e-05,
|
| 449 |
+
"loss": 18.8326,
|
| 450 |
+
"mean_token_accuracy": 0.7513993989676238,
|
| 451 |
+
"num_tokens": 10289883.0,
|
| 452 |
+
"step": 310
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"entropy": 1.114009590819478,
|
| 456 |
+
"epoch": 0.512,
|
| 457 |
+
"grad_norm": 15.4375,
|
| 458 |
+
"learning_rate": 1.985925925925926e-05,
|
| 459 |
+
"loss": 18.526,
|
| 460 |
+
"mean_token_accuracy": 0.7558605384081603,
|
| 461 |
+
"num_tokens": 10619468.0,
|
| 462 |
+
"step": 320
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"entropy": 1.126872155070305,
|
| 466 |
+
"epoch": 0.528,
|
| 467 |
+
"grad_norm": 13.5625,
|
| 468 |
+
"learning_rate": 1.9785185185185187e-05,
|
| 469 |
+
"loss": 18.6944,
|
| 470 |
+
"mean_token_accuracy": 0.75301427654922,
|
| 471 |
+
"num_tokens": 10944904.0,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"entropy": 1.11179842017591,
|
| 476 |
+
"epoch": 0.544,
|
| 477 |
+
"grad_norm": 14.625,
|
| 478 |
+
"learning_rate": 1.971111111111111e-05,
|
| 479 |
+
"loss": 18.3887,
|
| 480 |
+
"mean_token_accuracy": 0.7559159055352211,
|
| 481 |
+
"num_tokens": 11266409.0,
|
| 482 |
+
"step": 340
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"entropy": 1.0923905447125435,
|
| 486 |
+
"epoch": 0.56,
|
| 487 |
+
"grad_norm": 13.5,
|
| 488 |
+
"learning_rate": 1.963703703703704e-05,
|
| 489 |
+
"loss": 18.0431,
|
| 490 |
+
"mean_token_accuracy": 0.7601441144943237,
|
| 491 |
+
"num_tokens": 11605544.0,
|
| 492 |
+
"step": 350
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"entropy": 1.075535924360156,
|
| 496 |
+
"epoch": 0.576,
|
| 497 |
+
"grad_norm": 15.375,
|
| 498 |
+
"learning_rate": 1.9562962962962964e-05,
|
| 499 |
+
"loss": 17.9134,
|
| 500 |
+
"mean_token_accuracy": 0.762933773174882,
|
| 501 |
+
"num_tokens": 11931715.0,
|
| 502 |
+
"step": 360
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"entropy": 1.0857708267867565,
|
| 506 |
+
"epoch": 0.592,
|
| 507 |
+
"grad_norm": 16.5,
|
| 508 |
+
"learning_rate": 1.948888888888889e-05,
|
| 509 |
+
"loss": 17.9806,
|
| 510 |
+
"mean_token_accuracy": 0.7590868677943945,
|
| 511 |
+
"num_tokens": 12257243.0,
|
| 512 |
+
"step": 370
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"entropy": 1.077372272312641,
|
| 516 |
+
"epoch": 0.608,
|
| 517 |
+
"grad_norm": 14.25,
|
| 518 |
+
"learning_rate": 1.9414814814814817e-05,
|
| 519 |
+
"loss": 17.8473,
|
| 520 |
+
"mean_token_accuracy": 0.7623418286442757,
|
| 521 |
+
"num_tokens": 12583154.0,
|
| 522 |
+
"step": 380
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"entropy": 1.101408040151,
|
| 526 |
+
"epoch": 0.624,
|
| 527 |
+
"grad_norm": 13.4375,
|
| 528 |
+
"learning_rate": 1.9340740740740743e-05,
|
| 529 |
+
"loss": 18.1987,
|
| 530 |
+
"mean_token_accuracy": 0.7578636299818754,
|
| 531 |
+
"num_tokens": 12905392.0,
|
| 532 |
+
"step": 390
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"entropy": 1.0936459716409446,
|
| 536 |
+
"epoch": 0.64,
|
| 537 |
+
"grad_norm": 15.0,
|
| 538 |
+
"learning_rate": 1.926666666666667e-05,
|
| 539 |
+
"loss": 18.2164,
|
| 540 |
+
"mean_token_accuracy": 0.7581360317766667,
|
| 541 |
+
"num_tokens": 13232198.0,
|
| 542 |
+
"step": 400
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.64,
|
| 546 |
+
"eval_biology_entropy": 2.985183084487915,
|
| 547 |
+
"eval_biology_loss": 3.3934555053710938,
|
| 548 |
+
"eval_biology_mean_token_accuracy": 0.47690209436416625,
|
| 549 |
+
"eval_biology_num_tokens": 13232198.0,
|
| 550 |
+
"eval_biology_runtime": 56.2992,
|
| 551 |
+
"eval_biology_samples_per_second": 8.881,
|
| 552 |
+
"eval_biology_steps_per_second": 2.22,
|
| 553 |
+
"step": 400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.64,
|
| 557 |
+
"eval_chemistry_entropy": 1.5230218110084535,
|
| 558 |
+
"eval_chemistry_loss": 1.5974879264831543,
|
| 559 |
+
"eval_chemistry_mean_token_accuracy": 0.6924252939224244,
|
| 560 |
+
"eval_chemistry_num_tokens": 13232198.0,
|
| 561 |
+
"eval_chemistry_runtime": 69.6914,
|
| 562 |
+
"eval_chemistry_samples_per_second": 7.174,
|
| 563 |
+
"eval_chemistry_steps_per_second": 1.794,
|
| 564 |
+
"step": 400
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.64,
|
| 568 |
+
"eval_math_entropy": 1.0690260066986084,
|
| 569 |
+
"eval_math_loss": 1.3214365243911743,
|
| 570 |
+
"eval_math_mean_token_accuracy": 0.7313346996307373,
|
| 571 |
+
"eval_math_num_tokens": 13232198.0,
|
| 572 |
+
"eval_math_runtime": 71.8154,
|
| 573 |
+
"eval_math_samples_per_second": 6.962,
|
| 574 |
+
"eval_math_steps_per_second": 1.741,
|
| 575 |
+
"step": 400
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.64,
|
| 579 |
+
"eval_physics_entropy": 1.079647916316986,
|
| 580 |
+
"eval_physics_loss": 1.122850775718689,
|
| 581 |
+
"eval_physics_mean_token_accuracy": 0.7587474570274353,
|
| 582 |
+
"eval_physics_num_tokens": 13232198.0,
|
| 583 |
+
"eval_physics_runtime": 83.3676,
|
| 584 |
+
"eval_physics_samples_per_second": 5.998,
|
| 585 |
+
"eval_physics_steps_per_second": 1.499,
|
| 586 |
+
"step": 400
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 1.0861666969954968,
|
| 590 |
+
"epoch": 0.656,
|
| 591 |
+
"grad_norm": 14.1875,
|
| 592 |
+
"learning_rate": 1.9192592592592593e-05,
|
| 593 |
+
"loss": 17.9599,
|
| 594 |
+
"mean_token_accuracy": 0.7603602163493633,
|
| 595 |
+
"num_tokens": 13575902.0,
|
| 596 |
+
"step": 410
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 1.0595566183328629,
|
| 600 |
+
"epoch": 0.672,
|
| 601 |
+
"grad_norm": 15.5625,
|
| 602 |
+
"learning_rate": 1.911851851851852e-05,
|
| 603 |
+
"loss": 17.6133,
|
| 604 |
+
"mean_token_accuracy": 0.7644100178033113,
|
| 605 |
+
"num_tokens": 13895997.0,
|
| 606 |
+
"step": 420
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 1.0779153060168027,
|
| 610 |
+
"epoch": 0.688,
|
| 611 |
+
"grad_norm": 13.625,
|
| 612 |
+
"learning_rate": 1.9044444444444446e-05,
|
| 613 |
+
"loss": 17.708,
|
| 614 |
+
"mean_token_accuracy": 0.7641124926507473,
|
| 615 |
+
"num_tokens": 14234888.0,
|
| 616 |
+
"step": 430
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 1.0761012937873602,
|
| 620 |
+
"epoch": 0.704,
|
| 621 |
+
"grad_norm": 14.4375,
|
| 622 |
+
"learning_rate": 1.8970370370370372e-05,
|
| 623 |
+
"loss": 17.9412,
|
| 624 |
+
"mean_token_accuracy": 0.7593970015645027,
|
| 625 |
+
"num_tokens": 14567908.0,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 1.0635488711297512,
|
| 630 |
+
"epoch": 0.72,
|
| 631 |
+
"grad_norm": 15.5625,
|
| 632 |
+
"learning_rate": 1.8896296296296295e-05,
|
| 633 |
+
"loss": 17.5409,
|
| 634 |
+
"mean_token_accuracy": 0.7655271884053946,
|
| 635 |
+
"num_tokens": 14882927.0,
|
| 636 |
+
"step": 450
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 1.0563195772469043,
|
| 640 |
+
"epoch": 0.736,
|
| 641 |
+
"grad_norm": 15.8125,
|
| 642 |
+
"learning_rate": 1.8822222222222225e-05,
|
| 643 |
+
"loss": 17.5759,
|
| 644 |
+
"mean_token_accuracy": 0.7641396790742874,
|
| 645 |
+
"num_tokens": 15217342.0,
|
| 646 |
+
"step": 460
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 1.037678936868906,
|
| 650 |
+
"epoch": 0.752,
|
| 651 |
+
"grad_norm": 13.125,
|
| 652 |
+
"learning_rate": 1.874814814814815e-05,
|
| 653 |
+
"loss": 17.1107,
|
| 654 |
+
"mean_token_accuracy": 0.7690521724522114,
|
| 655 |
+
"num_tokens": 15547710.0,
|
| 656 |
+
"step": 470
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 1.0838343646377324,
|
| 660 |
+
"epoch": 0.768,
|
| 661 |
+
"grad_norm": 16.75,
|
| 662 |
+
"learning_rate": 1.8674074074074075e-05,
|
| 663 |
+
"loss": 18.0446,
|
| 664 |
+
"mean_token_accuracy": 0.759132880717516,
|
| 665 |
+
"num_tokens": 15877177.0,
|
| 666 |
+
"step": 480
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"entropy": 1.0296639803797007,
|
| 670 |
+
"epoch": 0.784,
|
| 671 |
+
"grad_norm": 12.5,
|
| 672 |
+
"learning_rate": 1.86e-05,
|
| 673 |
+
"loss": 17.1015,
|
| 674 |
+
"mean_token_accuracy": 0.7697366833686828,
|
| 675 |
+
"num_tokens": 16219640.0,
|
| 676 |
+
"step": 490
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"entropy": 1.0563473679125308,
|
| 680 |
+
"epoch": 0.8,
|
| 681 |
+
"grad_norm": 15.5,
|
| 682 |
+
"learning_rate": 1.8525925925925928e-05,
|
| 683 |
+
"loss": 17.5054,
|
| 684 |
+
"mean_token_accuracy": 0.7657136749476194,
|
| 685 |
+
"num_tokens": 16548261.0,
|
| 686 |
+
"step": 500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8,
|
| 690 |
+
"eval_biology_entropy": 2.9737762069702147,
|
| 691 |
+
"eval_biology_loss": 3.3795254230499268,
|
| 692 |
+
"eval_biology_mean_token_accuracy": 0.48070894145965576,
|
| 693 |
+
"eval_biology_num_tokens": 16548261.0,
|
| 694 |
+
"eval_biology_runtime": 56.18,
|
| 695 |
+
"eval_biology_samples_per_second": 8.9,
|
| 696 |
+
"eval_biology_steps_per_second": 2.225,
|
| 697 |
+
"step": 500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8,
|
| 701 |
+
"eval_chemistry_entropy": 1.5115246725082399,
|
| 702 |
+
"eval_chemistry_loss": 1.573546051979065,
|
| 703 |
+
"eval_chemistry_mean_token_accuracy": 0.6963776540756226,
|
| 704 |
+
"eval_chemistry_num_tokens": 16548261.0,
|
| 705 |
+
"eval_chemistry_runtime": 69.0701,
|
| 706 |
+
"eval_chemistry_samples_per_second": 7.239,
|
| 707 |
+
"eval_chemistry_steps_per_second": 1.81,
|
| 708 |
+
"step": 500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.8,
|
| 712 |
+
"eval_math_entropy": 1.0560337038040162,
|
| 713 |
+
"eval_math_loss": 1.306509017944336,
|
| 714 |
+
"eval_math_mean_token_accuracy": 0.7335917987823486,
|
| 715 |
+
"eval_math_num_tokens": 16548261.0,
|
| 716 |
+
"eval_math_runtime": 71.2835,
|
| 717 |
+
"eval_math_samples_per_second": 7.014,
|
| 718 |
+
"eval_math_steps_per_second": 1.754,
|
| 719 |
+
"step": 500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.8,
|
| 723 |
+
"eval_physics_entropy": 1.0595522990226747,
|
| 724 |
+
"eval_physics_loss": 1.0949721336364746,
|
| 725 |
+
"eval_physics_mean_token_accuracy": 0.7634064397811889,
|
| 726 |
+
"eval_physics_num_tokens": 16548261.0,
|
| 727 |
+
"eval_physics_runtime": 83.0981,
|
| 728 |
+
"eval_physics_samples_per_second": 6.017,
|
| 729 |
+
"eval_physics_steps_per_second": 1.504,
|
| 730 |
+
"step": 500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 1.042676868662238,
|
| 734 |
+
"epoch": 0.816,
|
| 735 |
+
"grad_norm": 14.1875,
|
| 736 |
+
"learning_rate": 1.8451851851851855e-05,
|
| 737 |
+
"loss": 17.3757,
|
| 738 |
+
"mean_token_accuracy": 0.7653235342353583,
|
| 739 |
+
"num_tokens": 16870533.0,
|
| 740 |
+
"step": 510
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 1.060330757498741,
|
| 744 |
+
"epoch": 0.832,
|
| 745 |
+
"grad_norm": 17.875,
|
| 746 |
+
"learning_rate": 1.8377777777777778e-05,
|
| 747 |
+
"loss": 17.5577,
|
| 748 |
+
"mean_token_accuracy": 0.7640024948865175,
|
| 749 |
+
"num_tokens": 17196371.0,
|
| 750 |
+
"step": 520
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 1.045187360420823,
|
| 754 |
+
"epoch": 0.848,
|
| 755 |
+
"grad_norm": 12.75,
|
| 756 |
+
"learning_rate": 1.8303703703703704e-05,
|
| 757 |
+
"loss": 17.2392,
|
| 758 |
+
"mean_token_accuracy": 0.7683587469160557,
|
| 759 |
+
"num_tokens": 17527066.0,
|
| 760 |
+
"step": 530
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 1.0516619730740786,
|
| 764 |
+
"epoch": 0.864,
|
| 765 |
+
"grad_norm": 13.9375,
|
| 766 |
+
"learning_rate": 1.822962962962963e-05,
|
| 767 |
+
"loss": 17.4228,
|
| 768 |
+
"mean_token_accuracy": 0.7653108265250921,
|
| 769 |
+
"num_tokens": 17859605.0,
|
| 770 |
+
"step": 540
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 1.0745812084525823,
|
| 774 |
+
"epoch": 0.88,
|
| 775 |
+
"grad_norm": 16.0,
|
| 776 |
+
"learning_rate": 1.8155555555555557e-05,
|
| 777 |
+
"loss": 17.7266,
|
| 778 |
+
"mean_token_accuracy": 0.7631923343986273,
|
| 779 |
+
"num_tokens": 18187315.0,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 0.9957344826310873,
|
| 784 |
+
"epoch": 0.896,
|
| 785 |
+
"grad_norm": 12.625,
|
| 786 |
+
"learning_rate": 1.8081481481481484e-05,
|
| 787 |
+
"loss": 16.4857,
|
| 788 |
+
"mean_token_accuracy": 0.7752151470631361,
|
| 789 |
+
"num_tokens": 18536790.0,
|
| 790 |
+
"step": 560
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 1.0575346298515798,
|
| 794 |
+
"epoch": 0.912,
|
| 795 |
+
"grad_norm": 14.9375,
|
| 796 |
+
"learning_rate": 1.800740740740741e-05,
|
| 797 |
+
"loss": 17.4739,
|
| 798 |
+
"mean_token_accuracy": 0.7637861587107182,
|
| 799 |
+
"num_tokens": 18869344.0,
|
| 800 |
+
"step": 570
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 1.0460248701274395,
|
| 804 |
+
"epoch": 0.928,
|
| 805 |
+
"grad_norm": 16.125,
|
| 806 |
+
"learning_rate": 1.7933333333333333e-05,
|
| 807 |
+
"loss": 17.3717,
|
| 808 |
+
"mean_token_accuracy": 0.7649744093418122,
|
| 809 |
+
"num_tokens": 19199834.0,
|
| 810 |
+
"step": 580
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 1.0241859197616576,
|
| 814 |
+
"epoch": 0.944,
|
| 815 |
+
"grad_norm": 15.5,
|
| 816 |
+
"learning_rate": 1.785925925925926e-05,
|
| 817 |
+
"loss": 16.9257,
|
| 818 |
+
"mean_token_accuracy": 0.7700011480599642,
|
| 819 |
+
"num_tokens": 19525385.0,
|
| 820 |
+
"step": 590
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 1.0272901140153408,
|
| 824 |
+
"epoch": 0.96,
|
| 825 |
+
"grad_norm": 17.125,
|
| 826 |
+
"learning_rate": 1.7785185185185186e-05,
|
| 827 |
+
"loss": 17.0788,
|
| 828 |
+
"mean_token_accuracy": 0.7674089819192886,
|
| 829 |
+
"num_tokens": 19856973.0,
|
| 830 |
+
"step": 600
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.96,
|
| 834 |
+
"eval_biology_entropy": 2.8927044954299928,
|
| 835 |
+
"eval_biology_loss": 3.3549082279205322,
|
| 836 |
+
"eval_biology_mean_token_accuracy": 0.48264122939109805,
|
| 837 |
+
"eval_biology_num_tokens": 19856973.0,
|
| 838 |
+
"eval_biology_runtime": 55.8568,
|
| 839 |
+
"eval_biology_samples_per_second": 8.951,
|
| 840 |
+
"eval_biology_steps_per_second": 2.238,
|
| 841 |
+
"step": 600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.96,
|
| 845 |
+
"eval_chemistry_entropy": 1.464129506111145,
|
| 846 |
+
"eval_chemistry_loss": 1.5512925386428833,
|
| 847 |
+
"eval_chemistry_mean_token_accuracy": 0.6986791820526123,
|
| 848 |
+
"eval_chemistry_num_tokens": 19856973.0,
|
| 849 |
+
"eval_chemistry_runtime": 69.6627,
|
| 850 |
+
"eval_chemistry_samples_per_second": 7.177,
|
| 851 |
+
"eval_chemistry_steps_per_second": 1.794,
|
| 852 |
+
"step": 600
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.96,
|
| 856 |
+
"eval_math_entropy": 1.0420140266418456,
|
| 857 |
+
"eval_math_loss": 1.297760248184204,
|
| 858 |
+
"eval_math_mean_token_accuracy": 0.7350094408988953,
|
| 859 |
+
"eval_math_num_tokens": 19856973.0,
|
| 860 |
+
"eval_math_runtime": 71.5855,
|
| 861 |
+
"eval_math_samples_per_second": 6.985,
|
| 862 |
+
"eval_math_steps_per_second": 1.746,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.96,
|
| 867 |
+
"eval_physics_entropy": 1.0300544242858887,
|
| 868 |
+
"eval_physics_loss": 1.076904058456421,
|
| 869 |
+
"eval_physics_mean_token_accuracy": 0.7661643705368042,
|
| 870 |
+
"eval_physics_num_tokens": 19856973.0,
|
| 871 |
+
"eval_physics_runtime": 83.7599,
|
| 872 |
+
"eval_physics_samples_per_second": 5.969,
|
| 873 |
+
"eval_physics_steps_per_second": 1.492,
|
| 874 |
+
"step": 600
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"entropy": 1.029942188039422,
|
| 878 |
+
"epoch": 0.976,
|
| 879 |
+
"grad_norm": 14.5625,
|
| 880 |
+
"learning_rate": 1.7711111111111113e-05,
|
| 881 |
+
"loss": 17.0833,
|
| 882 |
+
"mean_token_accuracy": 0.7702321965247393,
|
| 883 |
+
"num_tokens": 20190600.0,
|
| 884 |
+
"step": 610
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"entropy": 1.043160342797637,
|
| 888 |
+
"epoch": 0.992,
|
| 889 |
+
"grad_norm": 15.0,
|
| 890 |
+
"learning_rate": 1.763703703703704e-05,
|
| 891 |
+
"loss": 17.2354,
|
| 892 |
+
"mean_token_accuracy": 0.7673168186098337,
|
| 893 |
+
"num_tokens": 20518014.0,
|
| 894 |
+
"step": 620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"entropy": 1.0153347484767437,
|
| 898 |
+
"epoch": 1.008,
|
| 899 |
+
"grad_norm": 14.8125,
|
| 900 |
+
"learning_rate": 1.7562962962962962e-05,
|
| 901 |
+
"loss": 16.634,
|
| 902 |
+
"mean_token_accuracy": 0.7728456899523735,
|
| 903 |
+
"num_tokens": 20859215.0,
|
| 904 |
+
"step": 630
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"entropy": 1.010590048506856,
|
| 908 |
+
"epoch": 1.024,
|
| 909 |
+
"grad_norm": 15.25,
|
| 910 |
+
"learning_rate": 1.7488888888888892e-05,
|
| 911 |
+
"loss": 16.8635,
|
| 912 |
+
"mean_token_accuracy": 0.770306408405304,
|
| 913 |
+
"num_tokens": 21186658.0,
|
| 914 |
+
"step": 640
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"entropy": 1.0216664642095565,
|
| 918 |
+
"epoch": 1.04,
|
| 919 |
+
"grad_norm": 13.4375,
|
| 920 |
+
"learning_rate": 1.7414814814814815e-05,
|
| 921 |
+
"loss": 16.8228,
|
| 922 |
+
"mean_token_accuracy": 0.771704015135765,
|
| 923 |
+
"num_tokens": 21517237.0,
|
| 924 |
+
"step": 650
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"entropy": 0.9916718799620867,
|
| 928 |
+
"epoch": 1.056,
|
| 929 |
+
"grad_norm": 13.9375,
|
| 930 |
+
"learning_rate": 1.7340740740740742e-05,
|
| 931 |
+
"loss": 16.4977,
|
| 932 |
+
"mean_token_accuracy": 0.7741733457893133,
|
| 933 |
+
"num_tokens": 21852528.0,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"entropy": 1.0193660650402308,
|
| 938 |
+
"epoch": 1.072,
|
| 939 |
+
"grad_norm": 12.6875,
|
| 940 |
+
"learning_rate": 1.726666666666667e-05,
|
| 941 |
+
"loss": 16.7942,
|
| 942 |
+
"mean_token_accuracy": 0.7709830049425364,
|
| 943 |
+
"num_tokens": 22192380.0,
|
| 944 |
+
"step": 670
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"entropy": 1.017938245087862,
|
| 948 |
+
"epoch": 1.088,
|
| 949 |
+
"grad_norm": 17.5,
|
| 950 |
+
"learning_rate": 1.7192592592592595e-05,
|
| 951 |
+
"loss": 17.004,
|
| 952 |
+
"mean_token_accuracy": 0.7690784070640803,
|
| 953 |
+
"num_tokens": 22517971.0,
|
| 954 |
+
"step": 680
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"entropy": 1.009276295825839,
|
| 958 |
+
"epoch": 1.104,
|
| 959 |
+
"grad_norm": 13.5625,
|
| 960 |
+
"learning_rate": 1.711851851851852e-05,
|
| 961 |
+
"loss": 16.5871,
|
| 962 |
+
"mean_token_accuracy": 0.773436525464058,
|
| 963 |
+
"num_tokens": 22848694.0,
|
| 964 |
+
"step": 690
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"entropy": 1.0195886611938476,
|
| 968 |
+
"epoch": 1.12,
|
| 969 |
+
"grad_norm": 14.125,
|
| 970 |
+
"learning_rate": 1.7044444444444445e-05,
|
| 971 |
+
"loss": 17.0053,
|
| 972 |
+
"mean_token_accuracy": 0.7680860497057438,
|
| 973 |
+
"num_tokens": 23183889.0,
|
| 974 |
+
"step": 700
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.12,
|
| 978 |
+
"eval_biology_entropy": 2.837118970870972,
|
| 979 |
+
"eval_biology_loss": 3.3420016765594482,
|
| 980 |
+
"eval_biology_mean_token_accuracy": 0.48326786851882936,
|
| 981 |
+
"eval_biology_num_tokens": 23183889.0,
|
| 982 |
+
"eval_biology_runtime": 56.3022,
|
| 983 |
+
"eval_biology_samples_per_second": 8.881,
|
| 984 |
+
"eval_biology_steps_per_second": 2.22,
|
| 985 |
+
"step": 700
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.12,
|
| 989 |
+
"eval_chemistry_entropy": 1.433508418083191,
|
| 990 |
+
"eval_chemistry_loss": 1.5409785509109497,
|
| 991 |
+
"eval_chemistry_mean_token_accuracy": 0.6995256505012513,
|
| 992 |
+
"eval_chemistry_num_tokens": 23183889.0,
|
| 993 |
+
"eval_chemistry_runtime": 69.4682,
|
| 994 |
+
"eval_chemistry_samples_per_second": 7.198,
|
| 995 |
+
"eval_chemistry_steps_per_second": 1.799,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.12,
|
| 1000 |
+
"eval_math_entropy": 1.0230936131477355,
|
| 1001 |
+
"eval_math_loss": 1.2898101806640625,
|
| 1002 |
+
"eval_math_mean_token_accuracy": 0.736490508556366,
|
| 1003 |
+
"eval_math_num_tokens": 23183889.0,
|
| 1004 |
+
"eval_math_runtime": 71.817,
|
| 1005 |
+
"eval_math_samples_per_second": 6.962,
|
| 1006 |
+
"eval_math_steps_per_second": 1.741,
|
| 1007 |
+
"step": 700
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.12,
|
| 1011 |
+
"eval_physics_entropy": 1.0090678911209106,
|
| 1012 |
+
"eval_physics_loss": 1.062973976135254,
|
| 1013 |
+
"eval_physics_mean_token_accuracy": 0.7677445983886719,
|
| 1014 |
+
"eval_physics_num_tokens": 23183889.0,
|
| 1015 |
+
"eval_physics_runtime": 82.8728,
|
| 1016 |
+
"eval_physics_samples_per_second": 6.033,
|
| 1017 |
+
"eval_physics_steps_per_second": 1.508,
|
| 1018 |
+
"step": 700
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"entropy": 0.9851093973964453,
|
| 1022 |
+
"epoch": 1.1360000000000001,
|
| 1023 |
+
"grad_norm": 13.0625,
|
| 1024 |
+
"learning_rate": 1.697037037037037e-05,
|
| 1025 |
+
"loss": 16.2335,
|
| 1026 |
+
"mean_token_accuracy": 0.7770712476223707,
|
| 1027 |
+
"num_tokens": 23523903.0,
|
| 1028 |
+
"step": 710
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"entropy": 1.0010987296700478,
|
| 1032 |
+
"epoch": 1.152,
|
| 1033 |
+
"grad_norm": 16.375,
|
| 1034 |
+
"learning_rate": 1.6896296296296298e-05,
|
| 1035 |
+
"loss": 16.6749,
|
| 1036 |
+
"mean_token_accuracy": 0.7745790995657444,
|
| 1037 |
+
"num_tokens": 23848848.0,
|
| 1038 |
+
"step": 720
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"entropy": 1.0347776237875224,
|
| 1042 |
+
"epoch": 1.168,
|
| 1043 |
+
"grad_norm": 14.375,
|
| 1044 |
+
"learning_rate": 1.6822222222222224e-05,
|
| 1045 |
+
"loss": 16.9856,
|
| 1046 |
+
"mean_token_accuracy": 0.7672174524515867,
|
| 1047 |
+
"num_tokens": 24174589.0,
|
| 1048 |
+
"step": 730
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"entropy": 1.0073780696839094,
|
| 1052 |
+
"epoch": 1.184,
|
| 1053 |
+
"grad_norm": 16.875,
|
| 1054 |
+
"learning_rate": 1.6748148148148147e-05,
|
| 1055 |
+
"loss": 16.7297,
|
| 1056 |
+
"mean_token_accuracy": 0.7723128654062748,
|
| 1057 |
+
"num_tokens": 24495981.0,
|
| 1058 |
+
"step": 740
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"entropy": 0.9867725741118193,
|
| 1062 |
+
"epoch": 1.2,
|
| 1063 |
+
"grad_norm": 14.25,
|
| 1064 |
+
"learning_rate": 1.6674074074074077e-05,
|
| 1065 |
+
"loss": 16.3695,
|
| 1066 |
+
"mean_token_accuracy": 0.7768875520676375,
|
| 1067 |
+
"num_tokens": 24826245.0,
|
| 1068 |
+
"step": 750
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"entropy": 1.018533943966031,
|
| 1072 |
+
"epoch": 1.216,
|
| 1073 |
+
"grad_norm": 17.875,
|
| 1074 |
+
"learning_rate": 1.66e-05,
|
| 1075 |
+
"loss": 16.7892,
|
| 1076 |
+
"mean_token_accuracy": 0.7702058039605617,
|
| 1077 |
+
"num_tokens": 25147775.0,
|
| 1078 |
+
"step": 760
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"entropy": 0.9930577903985978,
|
| 1082 |
+
"epoch": 1.232,
|
| 1083 |
+
"grad_norm": 16.125,
|
| 1084 |
+
"learning_rate": 1.6525925925925927e-05,
|
| 1085 |
+
"loss": 16.5313,
|
| 1086 |
+
"mean_token_accuracy": 0.7744447194039822,
|
| 1087 |
+
"num_tokens": 25480033.0,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"entropy": 1.0064157444983721,
|
| 1092 |
+
"epoch": 1.248,
|
| 1093 |
+
"grad_norm": 15.8125,
|
| 1094 |
+
"learning_rate": 1.6451851851851853e-05,
|
| 1095 |
+
"loss": 16.6421,
|
| 1096 |
+
"mean_token_accuracy": 0.773406020924449,
|
| 1097 |
+
"num_tokens": 25811978.0,
|
| 1098 |
+
"step": 780
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"entropy": 0.9985887616872787,
|
| 1102 |
+
"epoch": 1.264,
|
| 1103 |
+
"grad_norm": 16.5,
|
| 1104 |
+
"learning_rate": 1.637777777777778e-05,
|
| 1105 |
+
"loss": 16.5153,
|
| 1106 |
+
"mean_token_accuracy": 0.774219336360693,
|
| 1107 |
+
"num_tokens": 26146299.0,
|
| 1108 |
+
"step": 790
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"entropy": 1.0295063827186823,
|
| 1112 |
+
"epoch": 1.28,
|
| 1113 |
+
"grad_norm": 16.125,
|
| 1114 |
+
"learning_rate": 1.6303703703703706e-05,
|
| 1115 |
+
"loss": 17.0668,
|
| 1116 |
+
"mean_token_accuracy": 0.7661171369254589,
|
| 1117 |
+
"num_tokens": 26478207.0,
|
| 1118 |
+
"step": 800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.28,
|
| 1122 |
+
"eval_biology_entropy": 2.898805745124817,
|
| 1123 |
+
"eval_biology_loss": 3.341296911239624,
|
| 1124 |
+
"eval_biology_mean_token_accuracy": 0.48686809062957764,
|
| 1125 |
+
"eval_biology_num_tokens": 26478207.0,
|
| 1126 |
+
"eval_biology_runtime": 56.3495,
|
| 1127 |
+
"eval_biology_samples_per_second": 8.873,
|
| 1128 |
+
"eval_biology_steps_per_second": 2.218,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.28,
|
| 1133 |
+
"eval_chemistry_entropy": 1.4466705160140991,
|
| 1134 |
+
"eval_chemistry_loss": 1.5262336730957031,
|
| 1135 |
+
"eval_chemistry_mean_token_accuracy": 0.7025133318901062,
|
| 1136 |
+
"eval_chemistry_num_tokens": 26478207.0,
|
| 1137 |
+
"eval_chemistry_runtime": 69.3655,
|
| 1138 |
+
"eval_chemistry_samples_per_second": 7.208,
|
| 1139 |
+
"eval_chemistry_steps_per_second": 1.802,
|
| 1140 |
+
"step": 800
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.28,
|
| 1144 |
+
"eval_math_entropy": 1.024560465335846,
|
| 1145 |
+
"eval_math_loss": 1.2816721200942993,
|
| 1146 |
+
"eval_math_mean_token_accuracy": 0.737667652130127,
|
| 1147 |
+
"eval_math_num_tokens": 26478207.0,
|
| 1148 |
+
"eval_math_runtime": 71.7104,
|
| 1149 |
+
"eval_math_samples_per_second": 6.972,
|
| 1150 |
+
"eval_math_steps_per_second": 1.743,
|
| 1151 |
+
"step": 800
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.28,
|
| 1155 |
+
"eval_physics_entropy": 1.0090858311653137,
|
| 1156 |
+
"eval_physics_loss": 1.0530790090560913,
|
| 1157 |
+
"eval_physics_mean_token_accuracy": 0.7696638231277466,
|
| 1158 |
+
"eval_physics_num_tokens": 26478207.0,
|
| 1159 |
+
"eval_physics_runtime": 83.3567,
|
| 1160 |
+
"eval_physics_samples_per_second": 5.998,
|
| 1161 |
+
"eval_physics_steps_per_second": 1.5,
|
| 1162 |
+
"step": 800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"entropy": 0.9791497606784105,
|
| 1166 |
+
"epoch": 1.296,
|
| 1167 |
+
"grad_norm": 15.9375,
|
| 1168 |
+
"learning_rate": 1.622962962962963e-05,
|
| 1169 |
+
"loss": 16.2738,
|
| 1170 |
+
"mean_token_accuracy": 0.777652832493186,
|
| 1171 |
+
"num_tokens": 26806477.0,
|
| 1172 |
+
"step": 810
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"entropy": 1.0318988490849734,
|
| 1176 |
+
"epoch": 1.312,
|
| 1177 |
+
"grad_norm": 17.125,
|
| 1178 |
+
"learning_rate": 1.6155555555555556e-05,
|
| 1179 |
+
"loss": 16.9474,
|
| 1180 |
+
"mean_token_accuracy": 0.7686588883399963,
|
| 1181 |
+
"num_tokens": 27137528.0,
|
| 1182 |
+
"step": 820
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"entropy": 1.007080302760005,
|
| 1186 |
+
"epoch": 1.328,
|
| 1187 |
+
"grad_norm": 17.875,
|
| 1188 |
+
"learning_rate": 1.6081481481481482e-05,
|
| 1189 |
+
"loss": 16.6844,
|
| 1190 |
+
"mean_token_accuracy": 0.771523043885827,
|
| 1191 |
+
"num_tokens": 27465859.0,
|
| 1192 |
+
"step": 830
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"entropy": 1.0098473474383354,
|
| 1196 |
+
"epoch": 1.3439999999999999,
|
| 1197 |
+
"grad_norm": 16.5,
|
| 1198 |
+
"learning_rate": 1.600740740740741e-05,
|
| 1199 |
+
"loss": 16.8087,
|
| 1200 |
+
"mean_token_accuracy": 0.7707158491015434,
|
| 1201 |
+
"num_tokens": 27795568.0,
|
| 1202 |
+
"step": 840
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"entropy": 1.0220563992857934,
|
| 1206 |
+
"epoch": 1.3599999999999999,
|
| 1207 |
+
"grad_norm": 15.3125,
|
| 1208 |
+
"learning_rate": 1.5933333333333336e-05,
|
| 1209 |
+
"loss": 16.768,
|
| 1210 |
+
"mean_token_accuracy": 0.770363200828433,
|
| 1211 |
+
"num_tokens": 28129988.0,
|
| 1212 |
+
"step": 850
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"entropy": 0.9859919909387826,
|
| 1216 |
+
"epoch": 1.376,
|
| 1217 |
+
"grad_norm": 17.875,
|
| 1218 |
+
"learning_rate": 1.5859259259259262e-05,
|
| 1219 |
+
"loss": 16.4135,
|
| 1220 |
+
"mean_token_accuracy": 0.7744484882801771,
|
| 1221 |
+
"num_tokens": 28465903.0,
|
| 1222 |
+
"step": 860
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"entropy": 0.988647548854351,
|
| 1226 |
+
"epoch": 1.392,
|
| 1227 |
+
"grad_norm": 17.125,
|
| 1228 |
+
"learning_rate": 1.5785185185185185e-05,
|
| 1229 |
+
"loss": 16.2043,
|
| 1230 |
+
"mean_token_accuracy": 0.7775332607328892,
|
| 1231 |
+
"num_tokens": 28801554.0,
|
| 1232 |
+
"step": 870
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"entropy": 0.9736344590783119,
|
| 1236 |
+
"epoch": 1.408,
|
| 1237 |
+
"grad_norm": 15.25,
|
| 1238 |
+
"learning_rate": 1.571111111111111e-05,
|
| 1239 |
+
"loss": 16.332,
|
| 1240 |
+
"mean_token_accuracy": 0.7759838547557593,
|
| 1241 |
+
"num_tokens": 29125114.0,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"entropy": 1.024445422179997,
|
| 1246 |
+
"epoch": 1.424,
|
| 1247 |
+
"grad_norm": 14.125,
|
| 1248 |
+
"learning_rate": 1.5637037037037038e-05,
|
| 1249 |
+
"loss": 16.9175,
|
| 1250 |
+
"mean_token_accuracy": 0.7679786011576653,
|
| 1251 |
+
"num_tokens": 29454334.0,
|
| 1252 |
+
"step": 890
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"entropy": 0.9635057615116238,
|
| 1256 |
+
"epoch": 1.44,
|
| 1257 |
+
"grad_norm": 15.4375,
|
| 1258 |
+
"learning_rate": 1.5562962962962965e-05,
|
| 1259 |
+
"loss": 15.9192,
|
| 1260 |
+
"mean_token_accuracy": 0.7802809584885836,
|
| 1261 |
+
"num_tokens": 29789253.0,
|
| 1262 |
+
"step": 900
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.44,
|
| 1266 |
+
"eval_biology_entropy": 2.8437174711227415,
|
| 1267 |
+
"eval_biology_loss": 3.318575143814087,
|
| 1268 |
+
"eval_biology_mean_token_accuracy": 0.4861623268127441,
|
| 1269 |
+
"eval_biology_num_tokens": 29789253.0,
|
| 1270 |
+
"eval_biology_runtime": 56.4644,
|
| 1271 |
+
"eval_biology_samples_per_second": 8.855,
|
| 1272 |
+
"eval_biology_steps_per_second": 2.214,
|
| 1273 |
+
"step": 900
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.44,
|
| 1277 |
+
"eval_chemistry_entropy": 1.420595220565796,
|
| 1278 |
+
"eval_chemistry_loss": 1.5160387754440308,
|
| 1279 |
+
"eval_chemistry_mean_token_accuracy": 0.7028642320632934,
|
| 1280 |
+
"eval_chemistry_num_tokens": 29789253.0,
|
| 1281 |
+
"eval_chemistry_runtime": 69.7177,
|
| 1282 |
+
"eval_chemistry_samples_per_second": 7.172,
|
| 1283 |
+
"eval_chemistry_steps_per_second": 1.793,
|
| 1284 |
+
"step": 900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.44,
|
| 1288 |
+
"eval_math_entropy": 1.0116905975341797,
|
| 1289 |
+
"eval_math_loss": 1.2779794931411743,
|
| 1290 |
+
"eval_math_mean_token_accuracy": 0.7384266419410705,
|
| 1291 |
+
"eval_math_num_tokens": 29789253.0,
|
| 1292 |
+
"eval_math_runtime": 71.6683,
|
| 1293 |
+
"eval_math_samples_per_second": 6.977,
|
| 1294 |
+
"eval_math_steps_per_second": 1.744,
|
| 1295 |
+
"step": 900
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.44,
|
| 1299 |
+
"eval_physics_entropy": 0.9905482964515686,
|
| 1300 |
+
"eval_physics_loss": 1.0435165166854858,
|
| 1301 |
+
"eval_physics_mean_token_accuracy": 0.770782280921936,
|
| 1302 |
+
"eval_physics_num_tokens": 29789253.0,
|
| 1303 |
+
"eval_physics_runtime": 83.2228,
|
| 1304 |
+
"eval_physics_samples_per_second": 6.008,
|
| 1305 |
+
"eval_physics_steps_per_second": 1.502,
|
| 1306 |
+
"step": 900
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"entropy": 0.9581953696906567,
|
| 1310 |
+
"epoch": 1.456,
|
| 1311 |
+
"grad_norm": 13.1875,
|
| 1312 |
+
"learning_rate": 1.548888888888889e-05,
|
| 1313 |
+
"loss": 15.9515,
|
| 1314 |
+
"mean_token_accuracy": 0.7805543716996908,
|
| 1315 |
+
"num_tokens": 30128576.0,
|
| 1316 |
+
"step": 910
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"entropy": 1.0345965854823589,
|
| 1320 |
+
"epoch": 1.472,
|
| 1321 |
+
"grad_norm": 17.125,
|
| 1322 |
+
"learning_rate": 1.5414814814814814e-05,
|
| 1323 |
+
"loss": 17.1026,
|
| 1324 |
+
"mean_token_accuracy": 0.7668049655854702,
|
| 1325 |
+
"num_tokens": 30452719.0,
|
| 1326 |
+
"step": 920
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"entropy": 1.0023833878338337,
|
| 1330 |
+
"epoch": 1.488,
|
| 1331 |
+
"grad_norm": 13.8125,
|
| 1332 |
+
"learning_rate": 1.5340740740740744e-05,
|
| 1333 |
+
"loss": 16.5595,
|
| 1334 |
+
"mean_token_accuracy": 0.7728984329849482,
|
| 1335 |
+
"num_tokens": 30782343.0,
|
| 1336 |
+
"step": 930
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"entropy": 0.9856885317713022,
|
| 1340 |
+
"epoch": 1.504,
|
| 1341 |
+
"grad_norm": 14.1875,
|
| 1342 |
+
"learning_rate": 1.5266666666666667e-05,
|
| 1343 |
+
"loss": 16.267,
|
| 1344 |
+
"mean_token_accuracy": 0.7769489102065563,
|
| 1345 |
+
"num_tokens": 31113238.0,
|
| 1346 |
+
"step": 940
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"entropy": 1.0002378012984992,
|
| 1350 |
+
"epoch": 1.52,
|
| 1351 |
+
"grad_norm": 15.4375,
|
| 1352 |
+
"learning_rate": 1.5192592592592594e-05,
|
| 1353 |
+
"loss": 16.5956,
|
| 1354 |
+
"mean_token_accuracy": 0.7721422206610441,
|
| 1355 |
+
"num_tokens": 31444589.0,
|
| 1356 |
+
"step": 950
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"entropy": 1.0214108165353537,
|
| 1360 |
+
"epoch": 1.536,
|
| 1361 |
+
"grad_norm": 17.625,
|
| 1362 |
+
"learning_rate": 1.5118518518518519e-05,
|
| 1363 |
+
"loss": 16.8896,
|
| 1364 |
+
"mean_token_accuracy": 0.7694170981645584,
|
| 1365 |
+
"num_tokens": 31774137.0,
|
| 1366 |
+
"step": 960
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"entropy": 0.9722279075533151,
|
| 1370 |
+
"epoch": 1.552,
|
| 1371 |
+
"grad_norm": 16.375,
|
| 1372 |
+
"learning_rate": 1.5044444444444445e-05,
|
| 1373 |
+
"loss": 16.0224,
|
| 1374 |
+
"mean_token_accuracy": 0.7783945810049773,
|
| 1375 |
+
"num_tokens": 32101776.0,
|
| 1376 |
+
"step": 970
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"entropy": 0.9741225987672806,
|
| 1380 |
+
"epoch": 1.568,
|
| 1381 |
+
"grad_norm": 15.25,
|
| 1382 |
+
"learning_rate": 1.497037037037037e-05,
|
| 1383 |
+
"loss": 16.145,
|
| 1384 |
+
"mean_token_accuracy": 0.778332832083106,
|
| 1385 |
+
"num_tokens": 32428021.0,
|
| 1386 |
+
"step": 980
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"entropy": 1.0168811423704027,
|
| 1390 |
+
"epoch": 1.584,
|
| 1391 |
+
"grad_norm": 16.5,
|
| 1392 |
+
"learning_rate": 1.4896296296296298e-05,
|
| 1393 |
+
"loss": 16.8197,
|
| 1394 |
+
"mean_token_accuracy": 0.7688806146383286,
|
| 1395 |
+
"num_tokens": 32752735.0,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"entropy": 1.0012462731450795,
|
| 1400 |
+
"epoch": 1.6,
|
| 1401 |
+
"grad_norm": 14.625,
|
| 1402 |
+
"learning_rate": 1.4822222222222225e-05,
|
| 1403 |
+
"loss": 16.6785,
|
| 1404 |
+
"mean_token_accuracy": 0.7718310851603747,
|
| 1405 |
+
"num_tokens": 33075822.0,
|
| 1406 |
+
"step": 1000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.6,
|
| 1410 |
+
"eval_biology_entropy": 2.871693316459656,
|
| 1411 |
+
"eval_biology_loss": 3.2952377796173096,
|
| 1412 |
+
"eval_biology_mean_token_accuracy": 0.48806494069099426,
|
| 1413 |
+
"eval_biology_num_tokens": 33075822.0,
|
| 1414 |
+
"eval_biology_runtime": 56.2343,
|
| 1415 |
+
"eval_biology_samples_per_second": 8.891,
|
| 1416 |
+
"eval_biology_steps_per_second": 2.223,
|
| 1417 |
+
"step": 1000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.6,
|
| 1421 |
+
"eval_chemistry_entropy": 1.435364501476288,
|
| 1422 |
+
"eval_chemistry_loss": 1.5101022720336914,
|
| 1423 |
+
"eval_chemistry_mean_token_accuracy": 0.7037839899063111,
|
| 1424 |
+
"eval_chemistry_num_tokens": 33075822.0,
|
| 1425 |
+
"eval_chemistry_runtime": 69.2005,
|
| 1426 |
+
"eval_chemistry_samples_per_second": 7.225,
|
| 1427 |
+
"eval_chemistry_steps_per_second": 1.806,
|
| 1428 |
+
"step": 1000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.6,
|
| 1432 |
+
"eval_math_entropy": 1.0202706332206726,
|
| 1433 |
+
"eval_math_loss": 1.2738072872161865,
|
| 1434 |
+
"eval_math_mean_token_accuracy": 0.7389369897842407,
|
| 1435 |
+
"eval_math_num_tokens": 33075822.0,
|
| 1436 |
+
"eval_math_runtime": 71.9142,
|
| 1437 |
+
"eval_math_samples_per_second": 6.953,
|
| 1438 |
+
"eval_math_steps_per_second": 1.738,
|
| 1439 |
+
"step": 1000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.6,
|
| 1443 |
+
"eval_physics_entropy": 0.9962421131134033,
|
| 1444 |
+
"eval_physics_loss": 1.0371240377426147,
|
| 1445 |
+
"eval_physics_mean_token_accuracy": 0.7717792973518371,
|
| 1446 |
+
"eval_physics_num_tokens": 33075822.0,
|
| 1447 |
+
"eval_physics_runtime": 83.5174,
|
| 1448 |
+
"eval_physics_samples_per_second": 5.987,
|
| 1449 |
+
"eval_physics_steps_per_second": 1.497,
|
| 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 sha256:99fae199773974506471525072c20d6088b07c2300f704c09a94a2b4fb6d778d
|
| 3 |
+
size 6417
|