Upload google/gemma-3-270m-it-mmlu_pro/checkpoint-39500
Browse files- .gitattributes +1 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/added_tokens.json +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/chat_template.jinja +47 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/config.json +55 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/model.safetensors +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/optimizer.pt +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_0.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_1.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_2.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_3.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_4.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_5.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_6.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_7.pth +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/scheduler.pt +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/special_tokens_map.json +33 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer.json +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer.model +3 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer_config.json +0 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/trainer_state.json +1094 -0
- google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/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 -%}
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3TextForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 2048,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention"
|
| 37 |
+
],
|
| 38 |
+
"max_position_embeddings": 32768,
|
| 39 |
+
"model_type": "gemma3_text",
|
| 40 |
+
"num_attention_heads": 4,
|
| 41 |
+
"num_hidden_layers": 18,
|
| 42 |
+
"num_key_value_heads": 1,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"problem_type": "single_label_classification",
|
| 45 |
+
"query_pre_attn_scalar": 256,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_local_base_freq": 10000.0,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 1000000.0,
|
| 50 |
+
"sliding_window": 512,
|
| 51 |
+
"transformers_version": "4.57.0",
|
| 52 |
+
"use_bidirectional_attention": false,
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"vocab_size": 262144
|
| 55 |
+
}
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:461d2b9411e96d9dafc990f32533120ea3b8bbba0640a14bb70c32f6fe676be7
|
| 3 |
+
size 536225696
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a57fbc99f48442fb93536edd9ed816c803b98b8d8753d048ed3d51e7c9f9ac51
|
| 3 |
+
size 1072600395
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc8125017ac64aaaf6b7b4d9fec3c97b36247e6f90303f4f65e7da22752a6021
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e6feb4e71a30bbd30fb817d57cf38086ff8afd570f5fb462a4d672dc5b9c7f4
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a783a95b392b2b425b72256e899035dee284c9de0ad7d762036e94693dc4f06
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84676a652b2e127a0f26e9e98aa79f894b6a28b744b6c6af7db9b1981b7e8118
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e404f18b3aced4d62989184b5ba490b18f3cfd416c392cac83f54a7cd7234908
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e808e76e90d6a465ee4ea62c07518ee045190927828be150142f6f13cb63efa
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4ff2843553f32d6779fa593223bb2bc6507b59dc0801501e96de5709554f0b
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a00cbd0fa2276ef03d7e54235bff23ff65e5559b2a4d871c31f6ccca7fc9a594
|
| 3 |
+
size 16389
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3494c805e517ad939ba54ad38ea90f5051d6f814cec2a5b0f1d515ca634f2d50
|
| 3 |
+
size 1465
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/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 |
+
}
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/trainer_state.json
ADDED
|
@@ -0,0 +1,1094 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5034989993754063,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 39500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00637340505538489,
|
| 14 |
+
"grad_norm": 280.0,
|
| 15 |
+
"learning_rate": 6.359928626051491e-06,
|
| 16 |
+
"loss": 5.4594,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01274681011076978,
|
| 21 |
+
"grad_norm": 100.0,
|
| 22 |
+
"learning_rate": 1.2732602600050984e-05,
|
| 23 |
+
"loss": 4.709,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01274681011076978,
|
| 28 |
+
"eval_accuracy": 0.7175561479002666,
|
| 29 |
+
"eval_auc": 0.7208985686302185,
|
| 30 |
+
"eval_f1": 0.6381847876292697,
|
| 31 |
+
"eval_loss": 4.532001972198486,
|
| 32 |
+
"eval_precision": 0.6933309621576436,
|
| 33 |
+
"eval_recall": 0.6326105710782597,
|
| 34 |
+
"eval_runtime": 236.3818,
|
| 35 |
+
"eval_samples_per_second": 1901.322,
|
| 36 |
+
"eval_steps_per_second": 3.714,
|
| 37 |
+
"step": 1000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01912021516615467,
|
| 41 |
+
"grad_norm": 368.0,
|
| 42 |
+
"learning_rate": 1.9105276574050474e-05,
|
| 43 |
+
"loss": 4.5852,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02549362022153956,
|
| 48 |
+
"grad_norm": 170.0,
|
| 49 |
+
"learning_rate": 2.547795054804996e-05,
|
| 50 |
+
"loss": 4.2857,
|
| 51 |
+
"step": 2000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02549362022153956,
|
| 55 |
+
"eval_accuracy": 0.7647461941357874,
|
| 56 |
+
"eval_auc": 0.7973974347114563,
|
| 57 |
+
"eval_f1": 0.701763515452194,
|
| 58 |
+
"eval_loss": 4.041171550750732,
|
| 59 |
+
"eval_precision": 0.7651343630299938,
|
| 60 |
+
"eval_recall": 0.6882129391743368,
|
| 61 |
+
"eval_runtime": 235.9253,
|
| 62 |
+
"eval_samples_per_second": 1905.002,
|
| 63 |
+
"eval_steps_per_second": 3.722,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.03186702527692445,
|
| 68 |
+
"grad_norm": 109.0,
|
| 69 |
+
"learning_rate": 3.1850624522049453e-05,
|
| 70 |
+
"loss": 3.8736,
|
| 71 |
+
"step": 2500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.03824043033230934,
|
| 75 |
+
"grad_norm": 44.5,
|
| 76 |
+
"learning_rate": 3.822329849604894e-05,
|
| 77 |
+
"loss": 3.6724,
|
| 78 |
+
"step": 3000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.03824043033230934,
|
| 82 |
+
"eval_accuracy": 0.8030896363903364,
|
| 83 |
+
"eval_auc": 0.8465206623077393,
|
| 84 |
+
"eval_f1": 0.7667088375827027,
|
| 85 |
+
"eval_loss": 3.5329034328460693,
|
| 86 |
+
"eval_precision": 0.793541421184558,
|
| 87 |
+
"eval_recall": 0.7536982564982242,
|
| 88 |
+
"eval_runtime": 235.8325,
|
| 89 |
+
"eval_samples_per_second": 1905.751,
|
| 90 |
+
"eval_steps_per_second": 3.723,
|
| 91 |
+
"step": 3000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.04461383538769423,
|
| 95 |
+
"grad_norm": 36.0,
|
| 96 |
+
"learning_rate": 4.459597247004843e-05,
|
| 97 |
+
"loss": 3.5882,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.05098724044307912,
|
| 102 |
+
"grad_norm": 37.75,
|
| 103 |
+
"learning_rate": 5.0968646444047927e-05,
|
| 104 |
+
"loss": 3.5063,
|
| 105 |
+
"step": 4000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05098724044307912,
|
| 109 |
+
"eval_accuracy": 0.8067920380564171,
|
| 110 |
+
"eval_auc": 0.8545748591423035,
|
| 111 |
+
"eval_f1": 0.7629704100530446,
|
| 112 |
+
"eval_loss": 3.482598304748535,
|
| 113 |
+
"eval_precision": 0.8125964117429191,
|
| 114 |
+
"eval_recall": 0.7454246487633156,
|
| 115 |
+
"eval_runtime": 235.9569,
|
| 116 |
+
"eval_samples_per_second": 1904.746,
|
| 117 |
+
"eval_steps_per_second": 3.721,
|
| 118 |
+
"step": 4000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.05736064549846401,
|
| 122 |
+
"grad_norm": 66.0,
|
| 123 |
+
"learning_rate": 5.734132041804742e-05,
|
| 124 |
+
"loss": 3.4417,
|
| 125 |
+
"step": 4500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.0637340505538489,
|
| 129 |
+
"grad_norm": 48.0,
|
| 130 |
+
"learning_rate": 6.37139943920469e-05,
|
| 131 |
+
"loss": 3.3849,
|
| 132 |
+
"step": 5000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.0637340505538489,
|
| 136 |
+
"eval_accuracy": 0.8106501897925854,
|
| 137 |
+
"eval_auc": 0.8611223697662354,
|
| 138 |
+
"eval_f1": 0.7847092912487569,
|
| 139 |
+
"eval_loss": 3.420646905899048,
|
| 140 |
+
"eval_precision": 0.7922936032572139,
|
| 141 |
+
"eval_recall": 0.778987144356641,
|
| 142 |
+
"eval_runtime": 236.031,
|
| 143 |
+
"eval_samples_per_second": 1904.148,
|
| 144 |
+
"eval_steps_per_second": 3.72,
|
| 145 |
+
"step": 5000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07010745560923379,
|
| 149 |
+
"grad_norm": 23.5,
|
| 150 |
+
"learning_rate": 7.008666836604639e-05,
|
| 151 |
+
"loss": 3.3603,
|
| 152 |
+
"step": 5500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07648086066461868,
|
| 156 |
+
"grad_norm": 27.75,
|
| 157 |
+
"learning_rate": 7.645934234004589e-05,
|
| 158 |
+
"loss": 3.344,
|
| 159 |
+
"step": 6000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07648086066461868,
|
| 163 |
+
"eval_accuracy": 0.8188337434751846,
|
| 164 |
+
"eval_auc": 0.8691284656524658,
|
| 165 |
+
"eval_f1": 0.7824235286935783,
|
| 166 |
+
"eval_loss": 3.3333048820495605,
|
| 167 |
+
"eval_precision": 0.8193413944376746,
|
| 168 |
+
"eval_recall": 0.7662003507186271,
|
| 169 |
+
"eval_runtime": 235.9449,
|
| 170 |
+
"eval_samples_per_second": 1904.843,
|
| 171 |
+
"eval_steps_per_second": 3.721,
|
| 172 |
+
"step": 6000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.08285426572000357,
|
| 176 |
+
"grad_norm": 20.5,
|
| 177 |
+
"learning_rate": 8.283201631404538e-05,
|
| 178 |
+
"loss": 3.2919,
|
| 179 |
+
"step": 6500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.08922767077538846,
|
| 183 |
+
"grad_norm": 17.25,
|
| 184 |
+
"learning_rate": 8.920469028804487e-05,
|
| 185 |
+
"loss": 3.27,
|
| 186 |
+
"step": 7000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.08922767077538846,
|
| 190 |
+
"eval_accuracy": 0.8203645441640449,
|
| 191 |
+
"eval_auc": 0.870448887348175,
|
| 192 |
+
"eval_f1": 0.7899083336048272,
|
| 193 |
+
"eval_loss": 3.292984962463379,
|
| 194 |
+
"eval_precision": 0.8111738927346904,
|
| 195 |
+
"eval_recall": 0.7779126528172351,
|
| 196 |
+
"eval_runtime": 235.9365,
|
| 197 |
+
"eval_samples_per_second": 1904.911,
|
| 198 |
+
"eval_steps_per_second": 3.721,
|
| 199 |
+
"step": 7000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.09560107583077335,
|
| 203 |
+
"grad_norm": 35.5,
|
| 204 |
+
"learning_rate": 9.557736426204435e-05,
|
| 205 |
+
"loss": 3.2578,
|
| 206 |
+
"step": 7500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.10197448088615824,
|
| 210 |
+
"grad_norm": 22.75,
|
| 211 |
+
"learning_rate": 0.0001,
|
| 212 |
+
"loss": 3.2406,
|
| 213 |
+
"step": 8000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.10197448088615824,
|
| 217 |
+
"eval_accuracy": 0.8261206217542798,
|
| 218 |
+
"eval_auc": 0.8779715895652771,
|
| 219 |
+
"eval_f1": 0.7968208595461465,
|
| 220 |
+
"eval_loss": 3.1795294284820557,
|
| 221 |
+
"eval_precision": 0.8180364024794908,
|
| 222 |
+
"eval_recall": 0.7846676093864756,
|
| 223 |
+
"eval_runtime": 235.8958,
|
| 224 |
+
"eval_samples_per_second": 1905.239,
|
| 225 |
+
"eval_steps_per_second": 3.722,
|
| 226 |
+
"step": 8000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.10834788594154313,
|
| 230 |
+
"grad_norm": 26.25,
|
| 231 |
+
"learning_rate": 0.0001,
|
| 232 |
+
"loss": 3.2028,
|
| 233 |
+
"step": 8500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11472129099692802,
|
| 237 |
+
"grad_norm": 14.625,
|
| 238 |
+
"learning_rate": 0.0001,
|
| 239 |
+
"loss": 3.1689,
|
| 240 |
+
"step": 9000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11472129099692802,
|
| 244 |
+
"eval_accuracy": 0.8285325228396353,
|
| 245 |
+
"eval_auc": 0.8811337947845459,
|
| 246 |
+
"eval_f1": 0.8013452045114392,
|
| 247 |
+
"eval_loss": 3.1494317054748535,
|
| 248 |
+
"eval_precision": 0.8182039479298111,
|
| 249 |
+
"eval_recall": 0.7908135604045534,
|
| 250 |
+
"eval_runtime": 235.9141,
|
| 251 |
+
"eval_samples_per_second": 1905.092,
|
| 252 |
+
"eval_steps_per_second": 3.722,
|
| 253 |
+
"step": 9000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.1210946960523129,
|
| 257 |
+
"grad_norm": 13.4375,
|
| 258 |
+
"learning_rate": 0.0001,
|
| 259 |
+
"loss": 3.1133,
|
| 260 |
+
"step": 9500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.1274681011076978,
|
| 264 |
+
"grad_norm": 36.0,
|
| 265 |
+
"learning_rate": 0.0001,
|
| 266 |
+
"loss": 3.0911,
|
| 267 |
+
"step": 10000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.1274681011076978,
|
| 271 |
+
"eval_accuracy": 0.8282343727054677,
|
| 272 |
+
"eval_auc": 0.8881419897079468,
|
| 273 |
+
"eval_f1": 0.8074358690960415,
|
| 274 |
+
"eval_loss": 3.1354596614837646,
|
| 275 |
+
"eval_precision": 0.8100602141990728,
|
| 276 |
+
"eval_recall": 0.8050712691013812,
|
| 277 |
+
"eval_runtime": 235.8981,
|
| 278 |
+
"eval_samples_per_second": 1905.221,
|
| 279 |
+
"eval_steps_per_second": 3.722,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.13384150616308269,
|
| 284 |
+
"grad_norm": 14.75,
|
| 285 |
+
"learning_rate": 0.0001,
|
| 286 |
+
"loss": 3.0308,
|
| 287 |
+
"step": 10500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.14021491121846757,
|
| 291 |
+
"grad_norm": 12.75,
|
| 292 |
+
"learning_rate": 0.0001,
|
| 293 |
+
"loss": 3.015,
|
| 294 |
+
"step": 11000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.14021491121846757,
|
| 298 |
+
"eval_accuracy": 0.8361620512729231,
|
| 299 |
+
"eval_auc": 0.8948841691017151,
|
| 300 |
+
"eval_f1": 0.8145356177908325,
|
| 301 |
+
"eval_loss": 3.019545555114746,
|
| 302 |
+
"eval_precision": 0.8209786628512243,
|
| 303 |
+
"eval_recall": 0.8093553565236841,
|
| 304 |
+
"eval_runtime": 235.8842,
|
| 305 |
+
"eval_samples_per_second": 1905.333,
|
| 306 |
+
"eval_steps_per_second": 3.722,
|
| 307 |
+
"step": 11000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.14658831627385246,
|
| 311 |
+
"grad_norm": 20.25,
|
| 312 |
+
"learning_rate": 0.0001,
|
| 313 |
+
"loss": 2.9743,
|
| 314 |
+
"step": 11500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.15296172132923735,
|
| 318 |
+
"grad_norm": 12.3125,
|
| 319 |
+
"learning_rate": 0.0001,
|
| 320 |
+
"loss": 2.9401,
|
| 321 |
+
"step": 12000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.15296172132923735,
|
| 325 |
+
"eval_accuracy": 0.8361954262879419,
|
| 326 |
+
"eval_auc": 0.8988780379295349,
|
| 327 |
+
"eval_f1": 0.8173352478602913,
|
| 328 |
+
"eval_loss": 3.0004172325134277,
|
| 329 |
+
"eval_precision": 0.8181878263931783,
|
| 330 |
+
"eval_recall": 0.8165118432863682,
|
| 331 |
+
"eval_runtime": 235.9073,
|
| 332 |
+
"eval_samples_per_second": 1905.147,
|
| 333 |
+
"eval_steps_per_second": 3.722,
|
| 334 |
+
"step": 12000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.15933512638462224,
|
| 338 |
+
"grad_norm": 15.25,
|
| 339 |
+
"learning_rate": 0.0001,
|
| 340 |
+
"loss": 2.908,
|
| 341 |
+
"step": 12500
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.16570853144000713,
|
| 345 |
+
"grad_norm": 13.875,
|
| 346 |
+
"learning_rate": 0.0001,
|
| 347 |
+
"loss": 2.8787,
|
| 348 |
+
"step": 13000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.16570853144000713,
|
| 352 |
+
"eval_accuracy": 0.8437960297082133,
|
| 353 |
+
"eval_auc": 0.9022700190544128,
|
| 354 |
+
"eval_f1": 0.8193442741933041,
|
| 355 |
+
"eval_loss": 2.874938726425171,
|
| 356 |
+
"eval_precision": 0.8361642928355996,
|
| 357 |
+
"eval_recall": 0.8085115166264416,
|
| 358 |
+
"eval_runtime": 235.9543,
|
| 359 |
+
"eval_samples_per_second": 1904.767,
|
| 360 |
+
"eval_steps_per_second": 3.721,
|
| 361 |
+
"step": 13000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.17208193649539202,
|
| 365 |
+
"grad_norm": 16.375,
|
| 366 |
+
"learning_rate": 0.0001,
|
| 367 |
+
"loss": 2.8756,
|
| 368 |
+
"step": 13500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.1784553415507769,
|
| 372 |
+
"grad_norm": 12.125,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 2.8368,
|
| 375 |
+
"step": 14000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.1784553415507769,
|
| 379 |
+
"eval_accuracy": 0.8476319314343691,
|
| 380 |
+
"eval_auc": 0.9060380458831787,
|
| 381 |
+
"eval_f1": 0.8228087161610238,
|
| 382 |
+
"eval_loss": 2.818519353866577,
|
| 383 |
+
"eval_precision": 0.8428622503963941,
|
| 384 |
+
"eval_recall": 0.8105203055669887,
|
| 385 |
+
"eval_runtime": 235.8665,
|
| 386 |
+
"eval_samples_per_second": 1905.476,
|
| 387 |
+
"eval_steps_per_second": 3.722,
|
| 388 |
+
"step": 14000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.1848287466061618,
|
| 392 |
+
"grad_norm": 17.625,
|
| 393 |
+
"learning_rate": 0.0001,
|
| 394 |
+
"loss": 2.815,
|
| 395 |
+
"step": 14500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.1912021516615467,
|
| 399 |
+
"grad_norm": 14.625,
|
| 400 |
+
"learning_rate": 0.0001,
|
| 401 |
+
"loss": 2.7892,
|
| 402 |
+
"step": 15000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.1912021516615467,
|
| 406 |
+
"eval_accuracy": 0.8496433323394995,
|
| 407 |
+
"eval_auc": 0.9092991948127747,
|
| 408 |
+
"eval_f1": 0.8246497759245118,
|
| 409 |
+
"eval_loss": 2.790006637573242,
|
| 410 |
+
"eval_precision": 0.8464656761081797,
|
| 411 |
+
"eval_recall": 0.8116097713844176,
|
| 412 |
+
"eval_runtime": 235.9319,
|
| 413 |
+
"eval_samples_per_second": 1904.948,
|
| 414 |
+
"eval_steps_per_second": 3.721,
|
| 415 |
+
"step": 15000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19757555671693158,
|
| 419 |
+
"grad_norm": 13.875,
|
| 420 |
+
"learning_rate": 0.0001,
|
| 421 |
+
"loss": 2.7762,
|
| 422 |
+
"step": 15500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.20394896177231647,
|
| 426 |
+
"grad_norm": 14.1875,
|
| 427 |
+
"learning_rate": 0.0001,
|
| 428 |
+
"loss": 2.7388,
|
| 429 |
+
"step": 16000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.20394896177231647,
|
| 433 |
+
"eval_accuracy": 0.8512942830824274,
|
| 434 |
+
"eval_auc": 0.9118760228157043,
|
| 435 |
+
"eval_f1": 0.8312896382532227,
|
| 436 |
+
"eval_loss": 2.753647565841675,
|
| 437 |
+
"eval_precision": 0.8390426673615496,
|
| 438 |
+
"eval_recall": 0.8251724666807414,
|
| 439 |
+
"eval_runtime": 235.9135,
|
| 440 |
+
"eval_samples_per_second": 1905.096,
|
| 441 |
+
"eval_steps_per_second": 3.722,
|
| 442 |
+
"step": 16000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.21032236682770136,
|
| 446 |
+
"grad_norm": 14.4375,
|
| 447 |
+
"learning_rate": 0.0001,
|
| 448 |
+
"loss": 2.739,
|
| 449 |
+
"step": 16500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.21669577188308625,
|
| 453 |
+
"grad_norm": 19.25,
|
| 454 |
+
"learning_rate": 0.0001,
|
| 455 |
+
"loss": 2.7192,
|
| 456 |
+
"step": 17000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.21669577188308625,
|
| 460 |
+
"eval_accuracy": 0.854524984536243,
|
| 461 |
+
"eval_auc": 0.9146767854690552,
|
| 462 |
+
"eval_f1": 0.8303229470241833,
|
| 463 |
+
"eval_loss": 2.7026894092559814,
|
| 464 |
+
"eval_precision": 0.8525518966758392,
|
| 465 |
+
"eval_recall": 0.8169920703438669,
|
| 466 |
+
"eval_runtime": 235.9956,
|
| 467 |
+
"eval_samples_per_second": 1904.434,
|
| 468 |
+
"eval_steps_per_second": 3.72,
|
| 469 |
+
"step": 17000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.22306917693847114,
|
| 473 |
+
"grad_norm": 16.875,
|
| 474 |
+
"learning_rate": 0.0001,
|
| 475 |
+
"loss": 2.7023,
|
| 476 |
+
"step": 17500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.22944258199385603,
|
| 480 |
+
"grad_norm": 13.125,
|
| 481 |
+
"learning_rate": 0.0001,
|
| 482 |
+
"loss": 2.6888,
|
| 483 |
+
"step": 18000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.22944258199385603,
|
| 487 |
+
"eval_accuracy": 0.8558866851490083,
|
| 488 |
+
"eval_auc": 0.916471540927887,
|
| 489 |
+
"eval_f1": 0.8312201448847177,
|
| 490 |
+
"eval_loss": 2.6786839962005615,
|
| 491 |
+
"eval_precision": 0.8560204841421162,
|
| 492 |
+
"eval_recall": 0.8168747132432559,
|
| 493 |
+
"eval_runtime": 235.8807,
|
| 494 |
+
"eval_samples_per_second": 1905.361,
|
| 495 |
+
"eval_steps_per_second": 3.722,
|
| 496 |
+
"step": 18000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.23581598704924092,
|
| 500 |
+
"grad_norm": 13.25,
|
| 501 |
+
"learning_rate": 0.0001,
|
| 502 |
+
"loss": 2.6453,
|
| 503 |
+
"step": 18500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.2421893921046258,
|
| 507 |
+
"grad_norm": 17.75,
|
| 508 |
+
"learning_rate": 0.0001,
|
| 509 |
+
"loss": 2.6318,
|
| 510 |
+
"step": 19000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.2421893921046258,
|
| 514 |
+
"eval_accuracy": 0.8580071111032,
|
| 515 |
+
"eval_auc": 0.9181417226791382,
|
| 516 |
+
"eval_f1": 0.8353620807604387,
|
| 517 |
+
"eval_loss": 2.646692991256714,
|
| 518 |
+
"eval_precision": 0.854392404869657,
|
| 519 |
+
"eval_recall": 0.8232679476079143,
|
| 520 |
+
"eval_runtime": 236.966,
|
| 521 |
+
"eval_samples_per_second": 1896.635,
|
| 522 |
+
"eval_steps_per_second": 3.705,
|
| 523 |
+
"step": 19000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.2485627971600107,
|
| 527 |
+
"grad_norm": 11.5625,
|
| 528 |
+
"learning_rate": 0.0001,
|
| 529 |
+
"loss": 2.6293,
|
| 530 |
+
"step": 19500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.2549362022153956,
|
| 534 |
+
"grad_norm": 12.875,
|
| 535 |
+
"learning_rate": 0.0001,
|
| 536 |
+
"loss": 2.6017,
|
| 537 |
+
"step": 20000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.2549362022153956,
|
| 541 |
+
"eval_accuracy": 0.8599740119883054,
|
| 542 |
+
"eval_auc": 0.9203953146934509,
|
| 543 |
+
"eval_f1": 0.8392022322375958,
|
| 544 |
+
"eval_loss": 2.6171152591705322,
|
| 545 |
+
"eval_precision": 0.8530874017696329,
|
| 546 |
+
"eval_recall": 0.8295022195226356,
|
| 547 |
+
"eval_runtime": 235.9321,
|
| 548 |
+
"eval_samples_per_second": 1904.946,
|
| 549 |
+
"eval_steps_per_second": 3.721,
|
| 550 |
+
"step": 20000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.2613096072707805,
|
| 554 |
+
"grad_norm": 17.625,
|
| 555 |
+
"learning_rate": 0.0001,
|
| 556 |
+
"loss": 2.6217,
|
| 557 |
+
"step": 20500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.26768301232616537,
|
| 561 |
+
"grad_norm": 14.3125,
|
| 562 |
+
"learning_rate": 0.0001,
|
| 563 |
+
"loss": 2.5889,
|
| 564 |
+
"step": 21000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.26768301232616537,
|
| 568 |
+
"eval_accuracy": 0.8611532625189682,
|
| 569 |
+
"eval_auc": 0.9224462509155273,
|
| 570 |
+
"eval_f1": 0.8408396987376525,
|
| 571 |
+
"eval_loss": 2.5873217582702637,
|
| 572 |
+
"eval_precision": 0.853855816993957,
|
| 573 |
+
"eval_recall": 0.8315778560709257,
|
| 574 |
+
"eval_runtime": 235.8945,
|
| 575 |
+
"eval_samples_per_second": 1905.25,
|
| 576 |
+
"eval_steps_per_second": 3.722,
|
| 577 |
+
"step": 21000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.2740564173815503,
|
| 581 |
+
"grad_norm": 11.1875,
|
| 582 |
+
"learning_rate": 0.0001,
|
| 583 |
+
"loss": 2.5848,
|
| 584 |
+
"step": 21500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.28042982243693515,
|
| 588 |
+
"grad_norm": 15.0625,
|
| 589 |
+
"learning_rate": 0.0001,
|
| 590 |
+
"loss": 2.5618,
|
| 591 |
+
"step": 22000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.28042982243693515,
|
| 595 |
+
"eval_accuracy": 0.8609263124168406,
|
| 596 |
+
"eval_auc": 0.9236695170402527,
|
| 597 |
+
"eval_f1": 0.8428097613168799,
|
| 598 |
+
"eval_loss": 2.586594820022583,
|
| 599 |
+
"eval_precision": 0.8491212608075118,
|
| 600 |
+
"eval_recall": 0.8376013596126513,
|
| 601 |
+
"eval_runtime": 235.8797,
|
| 602 |
+
"eval_samples_per_second": 1905.37,
|
| 603 |
+
"eval_steps_per_second": 3.722,
|
| 604 |
+
"step": 22000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.28680322749232007,
|
| 608 |
+
"grad_norm": 15.875,
|
| 609 |
+
"learning_rate": 0.0001,
|
| 610 |
+
"loss": 2.5587,
|
| 611 |
+
"step": 22500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.29317663254770493,
|
| 615 |
+
"grad_norm": 16.0,
|
| 616 |
+
"learning_rate": 0.0001,
|
| 617 |
+
"loss": 2.5198,
|
| 618 |
+
"step": 23000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.29317663254770493,
|
| 622 |
+
"eval_accuracy": 0.8641258638566387,
|
| 623 |
+
"eval_auc": 0.9258681535720825,
|
| 624 |
+
"eval_f1": 0.8433215002829988,
|
| 625 |
+
"eval_loss": 2.530731439590454,
|
| 626 |
+
"eval_precision": 0.8596180420798043,
|
| 627 |
+
"eval_recall": 0.8323607774926369,
|
| 628 |
+
"eval_runtime": 236.896,
|
| 629 |
+
"eval_samples_per_second": 1897.195,
|
| 630 |
+
"eval_steps_per_second": 3.706,
|
| 631 |
+
"step": 23000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.29955003760308985,
|
| 635 |
+
"grad_norm": 16.125,
|
| 636 |
+
"learning_rate": 0.0001,
|
| 637 |
+
"loss": 2.5324,
|
| 638 |
+
"step": 23500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.3059234426584747,
|
| 642 |
+
"grad_norm": 14.9375,
|
| 643 |
+
"learning_rate": 0.0001,
|
| 644 |
+
"loss": 2.522,
|
| 645 |
+
"step": 24000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.3059234426584747,
|
| 649 |
+
"eval_accuracy": 0.8645819890618951,
|
| 650 |
+
"eval_auc": 0.9265353083610535,
|
| 651 |
+
"eval_f1": 0.8449232507125215,
|
| 652 |
+
"eval_loss": 2.515869379043579,
|
| 653 |
+
"eval_precision": 0.8575695182961542,
|
| 654 |
+
"eval_recall": 0.8358181801726667,
|
| 655 |
+
"eval_runtime": 235.8798,
|
| 656 |
+
"eval_samples_per_second": 1905.369,
|
| 657 |
+
"eval_steps_per_second": 3.722,
|
| 658 |
+
"step": 24000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.3122968477138596,
|
| 662 |
+
"grad_norm": 13.75,
|
| 663 |
+
"learning_rate": 0.0001,
|
| 664 |
+
"loss": 2.498,
|
| 665 |
+
"step": 24500
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.3186702527692445,
|
| 669 |
+
"grad_norm": 16.25,
|
| 670 |
+
"learning_rate": 0.0001,
|
| 671 |
+
"loss": 2.486,
|
| 672 |
+
"step": 25000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.3186702527692445,
|
| 676 |
+
"eval_accuracy": 0.8657857146035716,
|
| 677 |
+
"eval_auc": 0.9282439947128296,
|
| 678 |
+
"eval_f1": 0.8459563365344265,
|
| 679 |
+
"eval_loss": 2.492276191711426,
|
| 680 |
+
"eval_precision": 0.8598189954610617,
|
| 681 |
+
"eval_recall": 0.8361893429769411,
|
| 682 |
+
"eval_runtime": 235.8558,
|
| 683 |
+
"eval_samples_per_second": 1905.563,
|
| 684 |
+
"eval_steps_per_second": 3.723,
|
| 685 |
+
"step": 25000
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.3250436578246294,
|
| 689 |
+
"grad_norm": 15.6875,
|
| 690 |
+
"learning_rate": 0.0001,
|
| 691 |
+
"loss": 2.4922,
|
| 692 |
+
"step": 25500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.33141706288001427,
|
| 696 |
+
"grad_norm": 14.875,
|
| 697 |
+
"learning_rate": 0.0001,
|
| 698 |
+
"loss": 2.4656,
|
| 699 |
+
"step": 26000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.33141706288001427,
|
| 703 |
+
"eval_accuracy": 0.8665488899470005,
|
| 704 |
+
"eval_auc": 0.929278552532196,
|
| 705 |
+
"eval_f1": 0.8470851473256837,
|
| 706 |
+
"eval_loss": 2.4791793823242188,
|
| 707 |
+
"eval_precision": 0.8601149529519857,
|
| 708 |
+
"eval_recall": 0.8377495469299366,
|
| 709 |
+
"eval_runtime": 235.9794,
|
| 710 |
+
"eval_samples_per_second": 1904.565,
|
| 711 |
+
"eval_steps_per_second": 3.721,
|
| 712 |
+
"step": 26000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.3377904679353992,
|
| 716 |
+
"grad_norm": 16.875,
|
| 717 |
+
"learning_rate": 0.0001,
|
| 718 |
+
"loss": 2.4566,
|
| 719 |
+
"step": 26500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.34416387299078405,
|
| 723 |
+
"grad_norm": 14.875,
|
| 724 |
+
"learning_rate": 0.0001,
|
| 725 |
+
"loss": 2.4475,
|
| 726 |
+
"step": 27000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.34416387299078405,
|
| 730 |
+
"eval_accuracy": 0.8678304905237207,
|
| 731 |
+
"eval_auc": 0.930943489074707,
|
| 732 |
+
"eval_f1": 0.847395770631417,
|
| 733 |
+
"eval_loss": 2.4564414024353027,
|
| 734 |
+
"eval_precision": 0.8646021959492661,
|
| 735 |
+
"eval_recall": 0.8359379618427593,
|
| 736 |
+
"eval_runtime": 235.96,
|
| 737 |
+
"eval_samples_per_second": 1904.721,
|
| 738 |
+
"eval_steps_per_second": 3.721,
|
| 739 |
+
"step": 27000
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.35053727804616897,
|
| 743 |
+
"grad_norm": 16.625,
|
| 744 |
+
"learning_rate": 0.0001,
|
| 745 |
+
"loss": 2.4558,
|
| 746 |
+
"step": 27500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.3569106831015538,
|
| 750 |
+
"grad_norm": 12.6875,
|
| 751 |
+
"learning_rate": 0.0001,
|
| 752 |
+
"loss": 2.4269,
|
| 753 |
+
"step": 28000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.3569106831015538,
|
| 757 |
+
"eval_accuracy": 0.8688740159933072,
|
| 758 |
+
"eval_auc": 0.931858241558075,
|
| 759 |
+
"eval_f1": 0.850913963051127,
|
| 760 |
+
"eval_loss": 2.438432216644287,
|
| 761 |
+
"eval_precision": 0.860130532609005,
|
| 762 |
+
"eval_recall": 0.8437573238621774,
|
| 763 |
+
"eval_runtime": 235.7882,
|
| 764 |
+
"eval_samples_per_second": 1906.109,
|
| 765 |
+
"eval_steps_per_second": 3.724,
|
| 766 |
+
"step": 28000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.36328408815693874,
|
| 770 |
+
"grad_norm": 14.75,
|
| 771 |
+
"learning_rate": 0.0001,
|
| 772 |
+
"loss": 2.4417,
|
| 773 |
+
"step": 28500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.3696574932123236,
|
| 777 |
+
"grad_norm": 14.625,
|
| 778 |
+
"learning_rate": 0.0001,
|
| 779 |
+
"loss": 2.4049,
|
| 780 |
+
"step": 29000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.3696574932123236,
|
| 784 |
+
"eval_accuracy": 0.8687049159172122,
|
| 785 |
+
"eval_auc": 0.9325141310691833,
|
| 786 |
+
"eval_f1": 0.8503633017719338,
|
| 787 |
+
"eval_loss": 2.4242045879364014,
|
| 788 |
+
"eval_precision": 0.8607433942000131,
|
| 789 |
+
"eval_recall": 0.8425017750352706,
|
| 790 |
+
"eval_runtime": 235.9336,
|
| 791 |
+
"eval_samples_per_second": 1904.934,
|
| 792 |
+
"eval_steps_per_second": 3.721,
|
| 793 |
+
"step": 29000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3760308982677085,
|
| 797 |
+
"grad_norm": 13.5625,
|
| 798 |
+
"learning_rate": 0.0001,
|
| 799 |
+
"loss": 2.4041,
|
| 800 |
+
"step": 29500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.3824043033230934,
|
| 804 |
+
"grad_norm": 16.75,
|
| 805 |
+
"learning_rate": 0.0001,
|
| 806 |
+
"loss": 2.4019,
|
| 807 |
+
"step": 30000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3824043033230934,
|
| 811 |
+
"eval_accuracy": 0.8692478161615173,
|
| 812 |
+
"eval_auc": 0.9345240592956543,
|
| 813 |
+
"eval_f1": 0.853530809841845,
|
| 814 |
+
"eval_loss": 2.423635959625244,
|
| 815 |
+
"eval_precision": 0.8562227161992152,
|
| 816 |
+
"eval_recall": 0.8510652656840554,
|
| 817 |
+
"eval_runtime": 235.9233,
|
| 818 |
+
"eval_samples_per_second": 1905.017,
|
| 819 |
+
"eval_steps_per_second": 3.722,
|
| 820 |
+
"step": 30000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.3887777083784783,
|
| 824 |
+
"grad_norm": 18.5,
|
| 825 |
+
"learning_rate": 0.0001,
|
| 826 |
+
"loss": 2.3713,
|
| 827 |
+
"step": 30500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.39515111343386317,
|
| 831 |
+
"grad_norm": 14.875,
|
| 832 |
+
"learning_rate": 0.0001,
|
| 833 |
+
"loss": 2.3798,
|
| 834 |
+
"step": 31000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.39515111343386317,
|
| 838 |
+
"eval_accuracy": 0.8717932173069478,
|
| 839 |
+
"eval_auc": 0.9350019097328186,
|
| 840 |
+
"eval_f1": 0.8538149679524644,
|
| 841 |
+
"eval_loss": 2.3812272548675537,
|
| 842 |
+
"eval_precision": 0.8645258042401223,
|
| 843 |
+
"eval_recall": 0.8457306918961859,
|
| 844 |
+
"eval_runtime": 236.9275,
|
| 845 |
+
"eval_samples_per_second": 1896.943,
|
| 846 |
+
"eval_steps_per_second": 3.706,
|
| 847 |
+
"step": 31000
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.4015245184892481,
|
| 851 |
+
"grad_norm": 14.875,
|
| 852 |
+
"learning_rate": 0.0001,
|
| 853 |
+
"loss": 2.3885,
|
| 854 |
+
"step": 31500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.40789792354463295,
|
| 858 |
+
"grad_norm": 14.9375,
|
| 859 |
+
"learning_rate": 0.0001,
|
| 860 |
+
"loss": 2.3697,
|
| 861 |
+
"step": 32000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.40789792354463295,
|
| 865 |
+
"eval_accuracy": 0.8725185676333554,
|
| 866 |
+
"eval_auc": 0.9362517595291138,
|
| 867 |
+
"eval_f1": 0.8536967960754542,
|
| 868 |
+
"eval_loss": 2.366279363632202,
|
| 869 |
+
"eval_precision": 0.8677993339914021,
|
| 870 |
+
"eval_recall": 0.8437154760316758,
|
| 871 |
+
"eval_runtime": 235.8823,
|
| 872 |
+
"eval_samples_per_second": 1905.349,
|
| 873 |
+
"eval_steps_per_second": 3.722,
|
| 874 |
+
"step": 32000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.41427132860001786,
|
| 878 |
+
"grad_norm": 15.3125,
|
| 879 |
+
"learning_rate": 0.0001,
|
| 880 |
+
"loss": 2.3609,
|
| 881 |
+
"step": 32500
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.4206447336554027,
|
| 885 |
+
"grad_norm": 14.6875,
|
| 886 |
+
"learning_rate": 0.0001,
|
| 887 |
+
"loss": 2.3457,
|
| 888 |
+
"step": 33000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.4206447336554027,
|
| 892 |
+
"eval_accuracy": 0.8736199431289744,
|
| 893 |
+
"eval_auc": 0.937017023563385,
|
| 894 |
+
"eval_f1": 0.8555537856349047,
|
| 895 |
+
"eval_loss": 2.3477745056152344,
|
| 896 |
+
"eval_precision": 0.8675405385181937,
|
| 897 |
+
"eval_recall": 0.8467145886295767,
|
| 898 |
+
"eval_runtime": 236.0095,
|
| 899 |
+
"eval_samples_per_second": 1904.321,
|
| 900 |
+
"eval_steps_per_second": 3.72,
|
| 901 |
+
"step": 33000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.42701813871078764,
|
| 905 |
+
"grad_norm": 15.9375,
|
| 906 |
+
"learning_rate": 0.0001,
|
| 907 |
+
"loss": 2.3372,
|
| 908 |
+
"step": 33500
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.4333915437661725,
|
| 912 |
+
"grad_norm": 15.125,
|
| 913 |
+
"learning_rate": 0.0001,
|
| 914 |
+
"loss": 2.3387,
|
| 915 |
+
"step": 34000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.4333915437661725,
|
| 919 |
+
"eval_accuracy": 0.8744187184884233,
|
| 920 |
+
"eval_auc": 0.9379249811172485,
|
| 921 |
+
"eval_f1": 0.8563329267012663,
|
| 922 |
+
"eval_loss": 2.3327484130859375,
|
| 923 |
+
"eval_precision": 0.8688335161622546,
|
| 924 |
+
"eval_recall": 0.8471966069466921,
|
| 925 |
+
"eval_runtime": 235.9082,
|
| 926 |
+
"eval_samples_per_second": 1905.139,
|
| 927 |
+
"eval_steps_per_second": 3.722,
|
| 928 |
+
"step": 34000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.4397649488215574,
|
| 932 |
+
"grad_norm": 13.5625,
|
| 933 |
+
"learning_rate": 0.0001,
|
| 934 |
+
"loss": 2.3124,
|
| 935 |
+
"step": 34500
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.4461383538769423,
|
| 939 |
+
"grad_norm": 15.0,
|
| 940 |
+
"learning_rate": 0.0001,
|
| 941 |
+
"loss": 2.3108,
|
| 942 |
+
"step": 35000
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.4461383538769423,
|
| 946 |
+
"eval_accuracy": 0.8752486438618897,
|
| 947 |
+
"eval_auc": 0.9388136267662048,
|
| 948 |
+
"eval_f1": 0.857440432905537,
|
| 949 |
+
"eval_loss": 2.3170506954193115,
|
| 950 |
+
"eval_precision": 0.8693945403391463,
|
| 951 |
+
"eval_recall": 0.8486030934280269,
|
| 952 |
+
"eval_runtime": 237.1783,
|
| 953 |
+
"eval_samples_per_second": 1894.937,
|
| 954 |
+
"eval_steps_per_second": 3.702,
|
| 955 |
+
"step": 35000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.4525117589323272,
|
| 959 |
+
"grad_norm": 16.5,
|
| 960 |
+
"learning_rate": 0.0001,
|
| 961 |
+
"loss": 2.3104,
|
| 962 |
+
"step": 35500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.45888516398771206,
|
| 966 |
+
"grad_norm": 21.0,
|
| 967 |
+
"learning_rate": 0.0001,
|
| 968 |
+
"loss": 2.3093,
|
| 969 |
+
"step": 36000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.45888516398771206,
|
| 973 |
+
"eval_accuracy": 0.8749304687187109,
|
| 974 |
+
"eval_auc": 0.9399862289428711,
|
| 975 |
+
"eval_f1": 0.859832853201925,
|
| 976 |
+
"eval_loss": 2.3292479515075684,
|
| 977 |
+
"eval_precision": 0.8627566786638952,
|
| 978 |
+
"eval_recall": 0.8571670902820068,
|
| 979 |
+
"eval_runtime": 235.9848,
|
| 980 |
+
"eval_samples_per_second": 1904.521,
|
| 981 |
+
"eval_steps_per_second": 3.721,
|
| 982 |
+
"step": 36000
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.465258569043097,
|
| 986 |
+
"grad_norm": 15.8125,
|
| 987 |
+
"learning_rate": 0.0001,
|
| 988 |
+
"loss": 2.3037,
|
| 989 |
+
"step": 36500
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.47163197409848184,
|
| 993 |
+
"grad_norm": 15.3125,
|
| 994 |
+
"learning_rate": 0.0001,
|
| 995 |
+
"loss": 2.2886,
|
| 996 |
+
"step": 37000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.47163197409848184,
|
| 1000 |
+
"eval_accuracy": 0.8750083437537547,
|
| 1001 |
+
"eval_auc": 0.9404018521308899,
|
| 1002 |
+
"eval_f1": 0.855230925034759,
|
| 1003 |
+
"eval_loss": 2.3024775981903076,
|
| 1004 |
+
"eval_precision": 0.8746376825597328,
|
| 1005 |
+
"eval_recall": 0.8426211541705337,
|
| 1006 |
+
"eval_runtime": 236.0698,
|
| 1007 |
+
"eval_samples_per_second": 1903.835,
|
| 1008 |
+
"eval_steps_per_second": 3.719,
|
| 1009 |
+
"step": 37000
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.47800537915386676,
|
| 1013 |
+
"grad_norm": 14.8125,
|
| 1014 |
+
"learning_rate": 0.0001,
|
| 1015 |
+
"loss": 2.2959,
|
| 1016 |
+
"step": 37500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.4843787842092516,
|
| 1020 |
+
"grad_norm": 16.625,
|
| 1021 |
+
"learning_rate": 0.0001,
|
| 1022 |
+
"loss": 2.2607,
|
| 1023 |
+
"step": 38000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.4843787842092516,
|
| 1027 |
+
"eval_accuracy": 0.877444719850124,
|
| 1028 |
+
"eval_auc": 0.941037118434906,
|
| 1029 |
+
"eval_f1": 0.8605285488101033,
|
| 1030 |
+
"eval_loss": 2.27842378616333,
|
| 1031 |
+
"eval_precision": 0.8704496429359335,
|
| 1032 |
+
"eval_recall": 0.8528732041380341,
|
| 1033 |
+
"eval_runtime": 236.143,
|
| 1034 |
+
"eval_samples_per_second": 1903.245,
|
| 1035 |
+
"eval_steps_per_second": 3.718,
|
| 1036 |
+
"step": 38000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.49075218926463654,
|
| 1040 |
+
"grad_norm": 14.6875,
|
| 1041 |
+
"learning_rate": 0.0001,
|
| 1042 |
+
"loss": 2.2675,
|
| 1043 |
+
"step": 38500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.4971255943200214,
|
| 1047 |
+
"grad_norm": 18.75,
|
| 1048 |
+
"learning_rate": 0.0001,
|
| 1049 |
+
"loss": 2.2426,
|
| 1050 |
+
"step": 39000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.4971255943200214,
|
| 1054 |
+
"eval_accuracy": 0.8774046698321014,
|
| 1055 |
+
"eval_auc": 0.9419523477554321,
|
| 1056 |
+
"eval_f1": 0.860408547862752,
|
| 1057 |
+
"eval_loss": 2.262415647506714,
|
| 1058 |
+
"eval_precision": 0.8705951091265102,
|
| 1059 |
+
"eval_recall": 0.8525912689551651,
|
| 1060 |
+
"eval_runtime": 236.1607,
|
| 1061 |
+
"eval_samples_per_second": 1903.103,
|
| 1062 |
+
"eval_steps_per_second": 3.718,
|
| 1063 |
+
"step": 39000
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.5034989993754063,
|
| 1067 |
+
"grad_norm": 16.75,
|
| 1068 |
+
"learning_rate": 0.0001,
|
| 1069 |
+
"loss": 2.2544,
|
| 1070 |
+
"step": 39500
|
| 1071 |
+
}
|
| 1072 |
+
],
|
| 1073 |
+
"logging_steps": 500,
|
| 1074 |
+
"max_steps": 78451,
|
| 1075 |
+
"num_input_tokens_seen": 0,
|
| 1076 |
+
"num_train_epochs": 1,
|
| 1077 |
+
"save_steps": 500,
|
| 1078 |
+
"stateful_callbacks": {
|
| 1079 |
+
"TrainerControl": {
|
| 1080 |
+
"args": {
|
| 1081 |
+
"should_epoch_stop": false,
|
| 1082 |
+
"should_evaluate": false,
|
| 1083 |
+
"should_log": false,
|
| 1084 |
+
"should_save": true,
|
| 1085 |
+
"should_training_stop": false
|
| 1086 |
+
},
|
| 1087 |
+
"attributes": {}
|
| 1088 |
+
}
|
| 1089 |
+
},
|
| 1090 |
+
"total_flos": 9.105054320734241e+18,
|
| 1091 |
+
"train_batch_size": 64,
|
| 1092 |
+
"trial_name": null,
|
| 1093 |
+
"trial_params": null
|
| 1094 |
+
}
|
google/gemma-3-270m-it-mmlu_pro/checkpoint-39500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88ef4a3915b8e9506ab39a5ba6141f508f9a71f0225eebc339973f2f4e19a361
|
| 3 |
+
size 5841
|