Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- chat_template.jinja +47 -0
- config.json +112 -0
- generation_config.json +14 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- trainer_state.json +1459 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip 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
|
|
|
|
|
|
| 33 |
*.zip 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
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 -%}
|
config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_bidirectional_attention": false,
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"vocab_size": 262208
|
| 94 |
+
},
|
| 95 |
+
"transformers_version": "4.57.0",
|
| 96 |
+
"use_cache": false,
|
| 97 |
+
"vision_config": {
|
| 98 |
+
"attention_dropout": 0.0,
|
| 99 |
+
"dtype": "bfloat16",
|
| 100 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 101 |
+
"hidden_size": 1152,
|
| 102 |
+
"image_size": 896,
|
| 103 |
+
"intermediate_size": 4304,
|
| 104 |
+
"layer_norm_eps": 1e-06,
|
| 105 |
+
"model_type": "siglip_vision_model",
|
| 106 |
+
"num_attention_heads": 16,
|
| 107 |
+
"num_channels": 3,
|
| 108 |
+
"num_hidden_layers": 27,
|
| 109 |
+
"patch_size": 14,
|
| 110 |
+
"vision_use_head": false
|
| 111 |
+
}
|
| 112 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
1,
|
| 8 |
+
106
|
| 9 |
+
],
|
| 10 |
+
"pad_token_id": 0,
|
| 11 |
+
"top_k": 64,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "4.57.0"
|
| 14 |
+
}
|
model-00001-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfb9d5f799487eb018a9c8d6464369d471a2a6944eeb4acf818e1148a2fe4409
|
| 3 |
+
size 4995986904
|
model-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bd07f1bc376422e60ecda93b75a391c7f51108d117d1cb10eb0b2298b18f4b8
|
| 3 |
+
size 4781835008
|
model-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0669b6abeaad713e35d3f8bde251e6f32ae4101c199ff44d0bb97a9ae2cf6535
|
| 3 |
+
size 4954909720
|
model-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c844e4fcac3213dde2983da59ff8db0e8fee899213e64fabf006054152bd49b
|
| 3 |
+
size 4907664584
|
model-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8776d00890b471b748e0c780c517e486d55c05bdbaf6f9f6557ebf5f91ce9bf8
|
| 3 |
+
size 4954909792
|
model-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7264a628e5c2949afd603a19eaea9c7350957b053e3245456f56bfe4b296d60d
|
| 3 |
+
size 4907664584
|
model-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85d4d068a5c74fa8140e38ddb36b94e291923d65232a12c144c808bcd576ee0b
|
| 3 |
+
size 4954909792
|
model-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aaa69d979f99978b2e59e2b1365731f9799a4dba6434000d5e4d0e54443b979
|
| 3 |
+
size 4907664584
|
model-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731575e0fa95e35be5a575edc140e72a9bac034592a074c7d3572d25631540fd
|
| 3 |
+
size 4954909792
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1586c3259d932c7c70549995cfe73a187ae8d51372ee6945dbb3d1078ce01a04
|
| 3 |
+
size 3586406144
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fadd57e082bf82594ea1d2468996cfeebacd27b3fdce4f0b6f310caf6dba917a
|
| 3 |
+
size 4027515024
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1459 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 202,
|
| 7 |
+
"global_step": 202,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009900990099009901,
|
| 14 |
+
"grad_norm": 152.50006103515625,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 15.6875,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019801980198019802,
|
| 21 |
+
"grad_norm": 155.11602783203125,
|
| 22 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 23 |
+
"loss": 15.8984,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0297029702970297,
|
| 28 |
+
"grad_norm": 39.620399475097656,
|
| 29 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 30 |
+
"loss": 11.7891,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.039603960396039604,
|
| 35 |
+
"grad_norm": 481.17474365234375,
|
| 36 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 37 |
+
"loss": 12.0391,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04950495049504951,
|
| 42 |
+
"grad_norm": 45.559226989746094,
|
| 43 |
+
"learning_rate": 7.272727272727273e-05,
|
| 44 |
+
"loss": 13.8828,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0594059405940594,
|
| 49 |
+
"grad_norm": 65.59961700439453,
|
| 50 |
+
"learning_rate": 9.090909090909092e-05,
|
| 51 |
+
"loss": 16.6641,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06930693069306931,
|
| 56 |
+
"grad_norm": 33.685943603515625,
|
| 57 |
+
"learning_rate": 0.00010909090909090909,
|
| 58 |
+
"loss": 15.5469,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07920792079207921,
|
| 63 |
+
"grad_norm": 73.23568725585938,
|
| 64 |
+
"learning_rate": 0.00012727272727272728,
|
| 65 |
+
"loss": 19.2344,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0891089108910891,
|
| 70 |
+
"grad_norm": 26.491865158081055,
|
| 71 |
+
"learning_rate": 0.00014545454545454546,
|
| 72 |
+
"loss": 14.6875,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09900990099009901,
|
| 77 |
+
"grad_norm": 29.270771026611328,
|
| 78 |
+
"learning_rate": 0.00016363636363636366,
|
| 79 |
+
"loss": 13.5625,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10891089108910891,
|
| 84 |
+
"grad_norm": 22.94576644897461,
|
| 85 |
+
"learning_rate": 0.00018181818181818183,
|
| 86 |
+
"loss": 13.8359,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1188118811881188,
|
| 91 |
+
"grad_norm": 19.714340209960938,
|
| 92 |
+
"learning_rate": 0.0002,
|
| 93 |
+
"loss": 13.4453,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12871287128712872,
|
| 98 |
+
"grad_norm": 29.34218406677246,
|
| 99 |
+
"learning_rate": 0.00019998782593171394,
|
| 100 |
+
"loss": 14.1328,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.13861386138613863,
|
| 105 |
+
"grad_norm": 15.325265884399414,
|
| 106 |
+
"learning_rate": 0.0001999513070203655,
|
| 107 |
+
"loss": 14.1484,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1485148514851485,
|
| 112 |
+
"grad_norm": 15.70521354675293,
|
| 113 |
+
"learning_rate": 0.00019989045314559295,
|
| 114 |
+
"loss": 13.1875,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15841584158415842,
|
| 119 |
+
"grad_norm": 13.77431869506836,
|
| 120 |
+
"learning_rate": 0.00019980528077049017,
|
| 121 |
+
"loss": 12.2109,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16831683168316833,
|
| 126 |
+
"grad_norm": 48.380741119384766,
|
| 127 |
+
"learning_rate": 0.00019969581293715296,
|
| 128 |
+
"loss": 12.6484,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1782178217821782,
|
| 133 |
+
"grad_norm": 13.91443157196045,
|
| 134 |
+
"learning_rate": 0.00019956207926044532,
|
| 135 |
+
"loss": 12.6172,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18811881188118812,
|
| 140 |
+
"grad_norm": 9.085782051086426,
|
| 141 |
+
"learning_rate": 0.00019940411591998748,
|
| 142 |
+
"loss": 11.7734,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19801980198019803,
|
| 147 |
+
"grad_norm": 8.792189598083496,
|
| 148 |
+
"learning_rate": 0.0001992219656503682,
|
| 149 |
+
"loss": 11.2812,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2079207920792079,
|
| 154 |
+
"grad_norm": 9.451997756958008,
|
| 155 |
+
"learning_rate": 0.0001990156777295835,
|
| 156 |
+
"loss": 10.9844,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.21782178217821782,
|
| 161 |
+
"grad_norm": 8.6239652633667,
|
| 162 |
+
"learning_rate": 0.00019878530796570528,
|
| 163 |
+
"loss": 10.3516,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.22772277227722773,
|
| 168 |
+
"grad_norm": 9.932726860046387,
|
| 169 |
+
"learning_rate": 0.00019853091868178316,
|
| 170 |
+
"loss": 10.2031,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2376237623762376,
|
| 175 |
+
"grad_norm": 5.901266098022461,
|
| 176 |
+
"learning_rate": 0.00019825257869898418,
|
| 177 |
+
"loss": 9.9297,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.24752475247524752,
|
| 182 |
+
"grad_norm": 4.901180744171143,
|
| 183 |
+
"learning_rate": 0.00019795036331797405,
|
| 184 |
+
"loss": 9.5938,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25742574257425743,
|
| 189 |
+
"grad_norm": 4.704899311065674,
|
| 190 |
+
"learning_rate": 0.00019762435429854577,
|
| 191 |
+
"loss": 9.5703,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.26732673267326734,
|
| 196 |
+
"grad_norm": 4.755985736846924,
|
| 197 |
+
"learning_rate": 0.00019727463983750077,
|
| 198 |
+
"loss": 9.5312,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.27722772277227725,
|
| 203 |
+
"grad_norm": 5.313395023345947,
|
| 204 |
+
"learning_rate": 0.00019690131454478858,
|
| 205 |
+
"loss": 9.3672,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2871287128712871,
|
| 210 |
+
"grad_norm": 6.608179092407227,
|
| 211 |
+
"learning_rate": 0.00019650447941791155,
|
| 212 |
+
"loss": 9.6875,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.297029702970297,
|
| 217 |
+
"grad_norm": 7.129603385925293,
|
| 218 |
+
"learning_rate": 0.0001960842418146016,
|
| 219 |
+
"loss": 9.6016,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3069306930693069,
|
| 224 |
+
"grad_norm": 1075.1676025390625,
|
| 225 |
+
"learning_rate": 0.00019564071542377596,
|
| 226 |
+
"loss": 18.0156,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.31683168316831684,
|
| 231 |
+
"grad_norm": 12.196839332580566,
|
| 232 |
+
"learning_rate": 0.00019517402023478062,
|
| 233 |
+
"loss": 10.8125,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.32673267326732675,
|
| 238 |
+
"grad_norm": 6.137757301330566,
|
| 239 |
+
"learning_rate": 0.0001946842825049289,
|
| 240 |
+
"loss": 10.0625,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.33663366336633666,
|
| 245 |
+
"grad_norm": 9.860557556152344,
|
| 246 |
+
"learning_rate": 0.00019417163472534456,
|
| 247 |
+
"loss": 10.1719,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3465346534653465,
|
| 252 |
+
"grad_norm": 9.4225435256958,
|
| 253 |
+
"learning_rate": 0.00019363621558511805,
|
| 254 |
+
"loss": 8.7197,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3564356435643564,
|
| 259 |
+
"grad_norm": 4.244920253753662,
|
| 260 |
+
"learning_rate": 0.00019307816993378662,
|
| 261 |
+
"loss": 9.5391,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.36633663366336633,
|
| 266 |
+
"grad_norm": 4.227206707000732,
|
| 267 |
+
"learning_rate": 0.00019249764874214732,
|
| 268 |
+
"loss": 9.3281,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.37623762376237624,
|
| 273 |
+
"grad_norm": 3.867461681365967,
|
| 274 |
+
"learning_rate": 0.00019189480906141413,
|
| 275 |
+
"loss": 9.0625,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.38613861386138615,
|
| 280 |
+
"grad_norm": 5.17470121383667,
|
| 281 |
+
"learning_rate": 0.00019126981398073008,
|
| 282 |
+
"loss": 9.1094,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.39603960396039606,
|
| 287 |
+
"grad_norm": 5.798826694488525,
|
| 288 |
+
"learning_rate": 0.00019062283258304612,
|
| 289 |
+
"loss": 9.3359,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.40594059405940597,
|
| 294 |
+
"grad_norm": 4.38295841217041,
|
| 295 |
+
"learning_rate": 0.0001899540398993781,
|
| 296 |
+
"loss": 9.4219,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4158415841584158,
|
| 301 |
+
"grad_norm": 4.414400577545166,
|
| 302 |
+
"learning_rate": 0.00018926361686145494,
|
| 303 |
+
"loss": 9.1016,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.42574257425742573,
|
| 308 |
+
"grad_norm": 4.6771559715271,
|
| 309 |
+
"learning_rate": 0.00018855175025277022,
|
| 310 |
+
"loss": 8.9219,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.43564356435643564,
|
| 315 |
+
"grad_norm": 4.436445713043213,
|
| 316 |
+
"learning_rate": 0.00018781863265805065,
|
| 317 |
+
"loss": 9.1562,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.44554455445544555,
|
| 322 |
+
"grad_norm": 3.0445127487182617,
|
| 323 |
+
"learning_rate": 0.00018706446241115537,
|
| 324 |
+
"loss": 9.0,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.45544554455445546,
|
| 329 |
+
"grad_norm": 13.921093940734863,
|
| 330 |
+
"learning_rate": 0.00018628944354141962,
|
| 331 |
+
"loss": 8.6484,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.46534653465346537,
|
| 336 |
+
"grad_norm": 7.534108638763428,
|
| 337 |
+
"learning_rate": 0.00018549378571845767,
|
| 338 |
+
"loss": 9.7734,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.4752475247524752,
|
| 343 |
+
"grad_norm": 3.2327933311462402,
|
| 344 |
+
"learning_rate": 0.00018467770419543998,
|
| 345 |
+
"loss": 9.375,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.48514851485148514,
|
| 350 |
+
"grad_norm": 4.523435115814209,
|
| 351 |
+
"learning_rate": 0.00018384141975085952,
|
| 352 |
+
"loss": 9.1406,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.49504950495049505,
|
| 357 |
+
"grad_norm": 83.07750701904297,
|
| 358 |
+
"learning_rate": 0.00018298515862880387,
|
| 359 |
+
"loss": 8.9531,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.504950495049505,
|
| 364 |
+
"grad_norm": 6.1501641273498535,
|
| 365 |
+
"learning_rate": 0.00018210915247774784,
|
| 366 |
+
"loss": 10.0547,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5148514851485149,
|
| 371 |
+
"grad_norm": 3.1539700031280518,
|
| 372 |
+
"learning_rate": 0.00018121363828788484,
|
| 373 |
+
"loss": 9.3359,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5247524752475248,
|
| 378 |
+
"grad_norm": 3.68802809715271,
|
| 379 |
+
"learning_rate": 0.0001802988583270126,
|
| 380 |
+
"loss": 9.1328,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5346534653465347,
|
| 385 |
+
"grad_norm": 3.102386713027954,
|
| 386 |
+
"learning_rate": 0.00017936506007499136,
|
| 387 |
+
"loss": 8.9609,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5445544554455446,
|
| 392 |
+
"grad_norm": 3.1378631591796875,
|
| 393 |
+
"learning_rate": 0.00017841249615679192,
|
| 394 |
+
"loss": 8.7891,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.5544554455445545,
|
| 399 |
+
"grad_norm": 3.207996129989624,
|
| 400 |
+
"learning_rate": 0.00017744142427415172,
|
| 401 |
+
"loss": 8.75,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5643564356435643,
|
| 406 |
+
"grad_norm": 4.185523509979248,
|
| 407 |
+
"learning_rate": 0.0001764521071358577,
|
| 408 |
+
"loss": 8.5781,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5742574257425742,
|
| 413 |
+
"grad_norm": 2.66141676902771,
|
| 414 |
+
"learning_rate": 0.00017544481238667426,
|
| 415 |
+
"loss": 8.6172,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5841584158415841,
|
| 420 |
+
"grad_norm": 4.6184258460998535,
|
| 421 |
+
"learning_rate": 0.00017441981253493607,
|
| 422 |
+
"loss": 8.625,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.594059405940594,
|
| 427 |
+
"grad_norm": 114.2392578125,
|
| 428 |
+
"learning_rate": 0.00017337738487882508,
|
| 429 |
+
"loss": 13.5,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6039603960396039,
|
| 434 |
+
"grad_norm": 6.742166996002197,
|
| 435 |
+
"learning_rate": 0.00017231781143135173,
|
| 436 |
+
"loss": 9.3594,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6138613861386139,
|
| 441 |
+
"grad_norm": 2.791332483291626,
|
| 442 |
+
"learning_rate": 0.00017124137884406054,
|
| 443 |
+
"loss": 8.9375,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6237623762376238,
|
| 448 |
+
"grad_norm": 7.167698383331299,
|
| 449 |
+
"learning_rate": 0.00017014837832948087,
|
| 450 |
+
"loss": 8.6094,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6336633663366337,
|
| 455 |
+
"grad_norm": 4.072234153747559,
|
| 456 |
+
"learning_rate": 0.00016903910558234393,
|
| 457 |
+
"loss": 8.9688,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6435643564356436,
|
| 462 |
+
"grad_norm": 4.949003219604492,
|
| 463 |
+
"learning_rate": 0.0001679138606995868,
|
| 464 |
+
"loss": 8.7266,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6534653465346535,
|
| 469 |
+
"grad_norm": 70.55978393554688,
|
| 470 |
+
"learning_rate": 0.00016677294809916597,
|
| 471 |
+
"loss": 8.9453,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6633663366336634,
|
| 476 |
+
"grad_norm": 4.001098155975342,
|
| 477 |
+
"learning_rate": 0.0001656166764377016,
|
| 478 |
+
"loss": 8.9453,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6732673267326733,
|
| 483 |
+
"grad_norm": 3.2970945835113525,
|
| 484 |
+
"learning_rate": 0.00016444535852697508,
|
| 485 |
+
"loss": 8.7578,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6831683168316832,
|
| 490 |
+
"grad_norm": 7.960860252380371,
|
| 491 |
+
"learning_rate": 0.00016325931124930266,
|
| 492 |
+
"loss": 8.4883,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.693069306930693,
|
| 497 |
+
"grad_norm": 4.774203300476074,
|
| 498 |
+
"learning_rate": 0.00016205885547180762,
|
| 499 |
+
"loss": 9.0859,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7029702970297029,
|
| 504 |
+
"grad_norm": 2.7817211151123047,
|
| 505 |
+
"learning_rate": 0.00016084431595961464,
|
| 506 |
+
"loss": 9.0234,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7128712871287128,
|
| 511 |
+
"grad_norm": 3.5456042289733887,
|
| 512 |
+
"learning_rate": 0.0001596160212879894,
|
| 513 |
+
"loss": 8.5508,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7227722772277227,
|
| 518 |
+
"grad_norm": 2.8811049461364746,
|
| 519 |
+
"learning_rate": 0.00015837430375344766,
|
| 520 |
+
"loss": 8.3203,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7326732673267327,
|
| 525 |
+
"grad_norm": 2.634841203689575,
|
| 526 |
+
"learning_rate": 0.00015711949928385742,
|
| 527 |
+
"loss": 8.2539,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.7425742574257426,
|
| 532 |
+
"grad_norm": 2.80352520942688,
|
| 533 |
+
"learning_rate": 0.0001558519473475585,
|
| 534 |
+
"loss": 8.3594,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7524752475247525,
|
| 539 |
+
"grad_norm": 2.983501434326172,
|
| 540 |
+
"learning_rate": 0.000154571990861525,
|
| 541 |
+
"loss": 8.3555,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7623762376237624,
|
| 546 |
+
"grad_norm": 2.525681972503662,
|
| 547 |
+
"learning_rate": 0.00015327997609859386,
|
| 548 |
+
"loss": 8.0117,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.7722772277227723,
|
| 553 |
+
"grad_norm": 2.6573147773742676,
|
| 554 |
+
"learning_rate": 0.0001519762525937862,
|
| 555 |
+
"loss": 8.1836,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7821782178217822,
|
| 560 |
+
"grad_norm": 3.265751361846924,
|
| 561 |
+
"learning_rate": 0.0001506611730497459,
|
| 562 |
+
"loss": 8.1836,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.7920792079207921,
|
| 567 |
+
"grad_norm": 3.280087947845459,
|
| 568 |
+
"learning_rate": 0.00014933509324132116,
|
| 569 |
+
"loss": 8.2617,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.801980198019802,
|
| 574 |
+
"grad_norm": 2.2106235027313232,
|
| 575 |
+
"learning_rate": 0.0001479983719193151,
|
| 576 |
+
"loss": 8.0078,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.8118811881188119,
|
| 581 |
+
"grad_norm": 2.518003225326538,
|
| 582 |
+
"learning_rate": 0.0001466513707134312,
|
| 583 |
+
"loss": 8.0078,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8217821782178217,
|
| 588 |
+
"grad_norm": 38.51225280761719,
|
| 589 |
+
"learning_rate": 0.00014529445403443965,
|
| 590 |
+
"loss": 7.7637,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8316831683168316,
|
| 595 |
+
"grad_norm": 5.821120738983154,
|
| 596 |
+
"learning_rate": 0.0001439279889755918,
|
| 597 |
+
"loss": 8.375,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8415841584158416,
|
| 602 |
+
"grad_norm": 3.276437282562256,
|
| 603 |
+
"learning_rate": 0.0001425523452133084,
|
| 604 |
+
"loss": 8.7188,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8514851485148515,
|
| 609 |
+
"grad_norm": 6.970194339752197,
|
| 610 |
+
"learning_rate": 0.00014116789490716954,
|
| 611 |
+
"loss": 8.5781,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8613861386138614,
|
| 616 |
+
"grad_norm": 94.84854125976562,
|
| 617 |
+
"learning_rate": 0.00013977501259923215,
|
| 618 |
+
"loss": 23.9531,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.8712871287128713,
|
| 623 |
+
"grad_norm": 4.508042335510254,
|
| 624 |
+
"learning_rate": 0.00013837407511270365,
|
| 625 |
+
"loss": 9.0234,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8811881188118812,
|
| 630 |
+
"grad_norm": 2.887805223464966,
|
| 631 |
+
"learning_rate": 0.00013696546144999786,
|
| 632 |
+
"loss": 8.375,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.8910891089108911,
|
| 637 |
+
"grad_norm": 2.4554858207702637,
|
| 638 |
+
"learning_rate": 0.00013554955269020195,
|
| 639 |
+
"loss": 8.3242,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.900990099009901,
|
| 644 |
+
"grad_norm": 2.6604201793670654,
|
| 645 |
+
"learning_rate": 0.00013412673188598092,
|
| 646 |
+
"loss": 8.207,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9108910891089109,
|
| 651 |
+
"grad_norm": 3.3090832233428955,
|
| 652 |
+
"learning_rate": 0.00013269738395994883,
|
| 653 |
+
"loss": 8.2266,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9207920792079208,
|
| 658 |
+
"grad_norm": 2.517388105392456,
|
| 659 |
+
"learning_rate": 0.00013126189560053352,
|
| 660 |
+
"loss": 8.1797,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9306930693069307,
|
| 665 |
+
"grad_norm": 2.1608598232269287,
|
| 666 |
+
"learning_rate": 0.00012982065515736418,
|
| 667 |
+
"loss": 7.9102,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.9405940594059405,
|
| 672 |
+
"grad_norm": 2.3422179222106934,
|
| 673 |
+
"learning_rate": 0.00012837405253620905,
|
| 674 |
+
"loss": 7.6211,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9504950495049505,
|
| 679 |
+
"grad_norm": 2.019343852996826,
|
| 680 |
+
"learning_rate": 0.00012692247909349243,
|
| 681 |
+
"loss": 7.8633,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9603960396039604,
|
| 686 |
+
"grad_norm": 2.547525405883789,
|
| 687 |
+
"learning_rate": 0.00012546632753041904,
|
| 688 |
+
"loss": 7.5391,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9702970297029703,
|
| 693 |
+
"grad_norm": 2.123288869857788,
|
| 694 |
+
"learning_rate": 0.00012400599178673483,
|
| 695 |
+
"loss": 7.6953,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.9801980198019802,
|
| 700 |
+
"grad_norm": 2.303816080093384,
|
| 701 |
+
"learning_rate": 0.00012254186693415222,
|
| 702 |
+
"loss": 7.8242,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.9900990099009901,
|
| 707 |
+
"grad_norm": 2.4239020347595215,
|
| 708 |
+
"learning_rate": 0.00012107434906946982,
|
| 709 |
+
"loss": 7.5977,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.0,
|
| 714 |
+
"grad_norm": 2.0720744132995605,
|
| 715 |
+
"learning_rate": 0.00011960383520741419,
|
| 716 |
+
"loss": 7.3789,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"checkpoint_runtime": 117.0071
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.00990099009901,
|
| 724 |
+
"grad_norm": 2.3910915851593018,
|
| 725 |
+
"learning_rate": 0.0001181307231732336,
|
| 726 |
+
"loss": 6.1016,
|
| 727 |
+
"step": 102
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.0198019801980198,
|
| 731 |
+
"grad_norm": 2.539257764816284,
|
| 732 |
+
"learning_rate": 0.00011665541149507239,
|
| 733 |
+
"loss": 7.4375,
|
| 734 |
+
"step": 103
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.0297029702970297,
|
| 738 |
+
"grad_norm": 2.1717493534088135,
|
| 739 |
+
"learning_rate": 0.0001151782992961554,
|
| 740 |
+
"loss": 7.2188,
|
| 741 |
+
"step": 104
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.0396039603960396,
|
| 745 |
+
"grad_norm": 2.1999051570892334,
|
| 746 |
+
"learning_rate": 0.0001136997861868109,
|
| 747 |
+
"loss": 7.7773,
|
| 748 |
+
"step": 105
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.0495049504950495,
|
| 752 |
+
"grad_norm": 20.015344619750977,
|
| 753 |
+
"learning_rate": 0.00011222027215636235,
|
| 754 |
+
"loss": 13.418,
|
| 755 |
+
"step": 106
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.0594059405940595,
|
| 759 |
+
"grad_norm": 3.3290457725524902,
|
| 760 |
+
"learning_rate": 0.00011074015746491722,
|
| 761 |
+
"loss": 7.6797,
|
| 762 |
+
"step": 107
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.0693069306930694,
|
| 766 |
+
"grad_norm": 2.3182663917541504,
|
| 767 |
+
"learning_rate": 0.00010925984253508279,
|
| 768 |
+
"loss": 7.4141,
|
| 769 |
+
"step": 108
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.0792079207920793,
|
| 773 |
+
"grad_norm": 2.7846322059631348,
|
| 774 |
+
"learning_rate": 0.00010777972784363765,
|
| 775 |
+
"loss": 7.5781,
|
| 776 |
+
"step": 109
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.0891089108910892,
|
| 780 |
+
"grad_norm": 3.0692903995513916,
|
| 781 |
+
"learning_rate": 0.00010630021381318915,
|
| 782 |
+
"loss": 7.207,
|
| 783 |
+
"step": 110
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.099009900990099,
|
| 787 |
+
"grad_norm": 2.5749456882476807,
|
| 788 |
+
"learning_rate": 0.0001048217007038446,
|
| 789 |
+
"loss": 6.8672,
|
| 790 |
+
"step": 111
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.108910891089109,
|
| 794 |
+
"grad_norm": 2.473937511444092,
|
| 795 |
+
"learning_rate": 0.00010334458850492763,
|
| 796 |
+
"loss": 6.7148,
|
| 797 |
+
"step": 112
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.118811881188119,
|
| 801 |
+
"grad_norm": 2.3984756469726562,
|
| 802 |
+
"learning_rate": 0.00010186927682676646,
|
| 803 |
+
"loss": 6.6914,
|
| 804 |
+
"step": 113
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.1287128712871288,
|
| 808 |
+
"grad_norm": 2.423884391784668,
|
| 809 |
+
"learning_rate": 0.00010039616479258587,
|
| 810 |
+
"loss": 7.0469,
|
| 811 |
+
"step": 114
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.1386138613861387,
|
| 815 |
+
"grad_norm": 3.279681921005249,
|
| 816 |
+
"learning_rate": 9.892565093053024e-05,
|
| 817 |
+
"loss": 6.5078,
|
| 818 |
+
"step": 115
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.1485148514851484,
|
| 822 |
+
"grad_norm": 3.0356831550598145,
|
| 823 |
+
"learning_rate": 9.745813306584781e-05,
|
| 824 |
+
"loss": 6.5273,
|
| 825 |
+
"step": 116
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.1584158415841583,
|
| 829 |
+
"grad_norm": 2.747650146484375,
|
| 830 |
+
"learning_rate": 9.599400821326521e-05,
|
| 831 |
+
"loss": 6.4219,
|
| 832 |
+
"step": 117
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.1683168316831682,
|
| 836 |
+
"grad_norm": 2.4899802207946777,
|
| 837 |
+
"learning_rate": 9.453367246958095e-05,
|
| 838 |
+
"loss": 7.0586,
|
| 839 |
+
"step": 118
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.1782178217821782,
|
| 843 |
+
"grad_norm": 2.7331626415252686,
|
| 844 |
+
"learning_rate": 9.307752090650759e-05,
|
| 845 |
+
"loss": 6.3047,
|
| 846 |
+
"step": 119
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.188118811881188,
|
| 850 |
+
"grad_norm": 2.377115488052368,
|
| 851 |
+
"learning_rate": 9.162594746379097e-05,
|
| 852 |
+
"loss": 5.9258,
|
| 853 |
+
"step": 120
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.198019801980198,
|
| 857 |
+
"grad_norm": 2.8060243129730225,
|
| 858 |
+
"learning_rate": 9.017934484263584e-05,
|
| 859 |
+
"loss": 5.6406,
|
| 860 |
+
"step": 121
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.2079207920792079,
|
| 864 |
+
"grad_norm": 2.350632429122925,
|
| 865 |
+
"learning_rate": 8.873810439946648e-05,
|
| 866 |
+
"loss": 5.5859,
|
| 867 |
+
"step": 122
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.2178217821782178,
|
| 871 |
+
"grad_norm": 2.519296169281006,
|
| 872 |
+
"learning_rate": 8.73026160400512e-05,
|
| 873 |
+
"loss": 5.1758,
|
| 874 |
+
"step": 123
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.2277227722772277,
|
| 878 |
+
"grad_norm": 2.0400750637054443,
|
| 879 |
+
"learning_rate": 8.58732681140191e-05,
|
| 880 |
+
"loss": 5.5195,
|
| 881 |
+
"step": 124
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.2376237623762376,
|
| 885 |
+
"grad_norm": 1.9192492961883545,
|
| 886 |
+
"learning_rate": 8.445044730979808e-05,
|
| 887 |
+
"loss": 4.6875,
|
| 888 |
+
"step": 125
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.2475247524752475,
|
| 892 |
+
"grad_norm": 2.3437716960906982,
|
| 893 |
+
"learning_rate": 8.303453855000217e-05,
|
| 894 |
+
"loss": 4.4492,
|
| 895 |
+
"step": 126
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.2574257425742574,
|
| 899 |
+
"grad_norm": 2.027672052383423,
|
| 900 |
+
"learning_rate": 8.162592488729637e-05,
|
| 901 |
+
"loss": 4.3867,
|
| 902 |
+
"step": 127
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.2673267326732673,
|
| 906 |
+
"grad_norm": 2.480762243270874,
|
| 907 |
+
"learning_rate": 8.022498740076788e-05,
|
| 908 |
+
"loss": 4.582,
|
| 909 |
+
"step": 128
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.2772277227722773,
|
| 913 |
+
"grad_norm": 2.1822168827056885,
|
| 914 |
+
"learning_rate": 7.883210509283048e-05,
|
| 915 |
+
"loss": 4.6445,
|
| 916 |
+
"step": 129
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.2871287128712872,
|
| 920 |
+
"grad_norm": 2.1713345050811768,
|
| 921 |
+
"learning_rate": 7.74476547866916e-05,
|
| 922 |
+
"loss": 4.8281,
|
| 923 |
+
"step": 130
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.297029702970297,
|
| 927 |
+
"grad_norm": 2.949915885925293,
|
| 928 |
+
"learning_rate": 7.607201102440822e-05,
|
| 929 |
+
"loss": 4.8945,
|
| 930 |
+
"step": 131
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.306930693069307,
|
| 934 |
+
"grad_norm": 5.816825866699219,
|
| 935 |
+
"learning_rate": 7.470554596556038e-05,
|
| 936 |
+
"loss": 6.4536,
|
| 937 |
+
"step": 132
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.316831683168317,
|
| 941 |
+
"grad_norm": 2.8560147285461426,
|
| 942 |
+
"learning_rate": 7.334862928656882e-05,
|
| 943 |
+
"loss": 6.2148,
|
| 944 |
+
"step": 133
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.3267326732673268,
|
| 948 |
+
"grad_norm": 1.9923173189163208,
|
| 949 |
+
"learning_rate": 7.200162808068492e-05,
|
| 950 |
+
"loss": 4.8516,
|
| 951 |
+
"step": 134
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.3366336633663367,
|
| 955 |
+
"grad_norm": 3.521530866622925,
|
| 956 |
+
"learning_rate": 7.06649067586789e-05,
|
| 957 |
+
"loss": 5.7188,
|
| 958 |
+
"step": 135
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.3465346534653464,
|
| 962 |
+
"grad_norm": 32.16452407836914,
|
| 963 |
+
"learning_rate": 6.933882695025414e-05,
|
| 964 |
+
"loss": 6.3516,
|
| 965 |
+
"step": 136
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.3564356435643563,
|
| 969 |
+
"grad_norm": 2.6356420516967773,
|
| 970 |
+
"learning_rate": 6.802374740621382e-05,
|
| 971 |
+
"loss": 4.4414,
|
| 972 |
+
"step": 137
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.3663366336633662,
|
| 976 |
+
"grad_norm": 1.9716286659240723,
|
| 977 |
+
"learning_rate": 6.672002390140615e-05,
|
| 978 |
+
"loss": 4.2656,
|
| 979 |
+
"step": 138
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 1.3762376237623761,
|
| 983 |
+
"grad_norm": 1.7040444612503052,
|
| 984 |
+
"learning_rate": 6.542800913847502e-05,
|
| 985 |
+
"loss": 3.9785,
|
| 986 |
+
"step": 139
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.386138613861386,
|
| 990 |
+
"grad_norm": 2.3597848415374756,
|
| 991 |
+
"learning_rate": 6.414805265244153e-05,
|
| 992 |
+
"loss": 4.4141,
|
| 993 |
+
"step": 140
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.396039603960396,
|
| 997 |
+
"grad_norm": 2.488919734954834,
|
| 998 |
+
"learning_rate": 6.288050071614263e-05,
|
| 999 |
+
"loss": 4.8203,
|
| 1000 |
+
"step": 141
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.4059405940594059,
|
| 1004 |
+
"grad_norm": 2.223335027694702,
|
| 1005 |
+
"learning_rate": 6.162569624655235e-05,
|
| 1006 |
+
"loss": 4.1738,
|
| 1007 |
+
"step": 142
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.4158415841584158,
|
| 1011 |
+
"grad_norm": 1.9648133516311646,
|
| 1012 |
+
"learning_rate": 6.0383978712010627e-05,
|
| 1013 |
+
"loss": 4.0176,
|
| 1014 |
+
"step": 143
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.4257425742574257,
|
| 1018 |
+
"grad_norm": 2.9666850566864014,
|
| 1019 |
+
"learning_rate": 5.9155684040385396e-05,
|
| 1020 |
+
"loss": 4.4258,
|
| 1021 |
+
"step": 144
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.4356435643564356,
|
| 1025 |
+
"grad_norm": 2.051849603652954,
|
| 1026 |
+
"learning_rate": 5.794114452819239e-05,
|
| 1027 |
+
"loss": 4.0508,
|
| 1028 |
+
"step": 145
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.4455445544554455,
|
| 1032 |
+
"grad_norm": 1.7934975624084473,
|
| 1033 |
+
"learning_rate": 5.674068875069736e-05,
|
| 1034 |
+
"loss": 3.6016,
|
| 1035 |
+
"step": 146
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.4554455445544554,
|
| 1039 |
+
"grad_norm": 4.365362167358398,
|
| 1040 |
+
"learning_rate": 5.5554641473024916e-05,
|
| 1041 |
+
"loss": 6.043,
|
| 1042 |
+
"step": 147
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.4653465346534653,
|
| 1046 |
+
"grad_norm": 2.678313732147217,
|
| 1047 |
+
"learning_rate": 5.4383323562298405e-05,
|
| 1048 |
+
"loss": 5.1289,
|
| 1049 |
+
"step": 148
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.4752475247524752,
|
| 1053 |
+
"grad_norm": 1.8244177103042603,
|
| 1054 |
+
"learning_rate": 5.3227051900834024e-05,
|
| 1055 |
+
"loss": 3.7969,
|
| 1056 |
+
"step": 149
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.4851485148514851,
|
| 1060 |
+
"grad_norm": 1.8080298900604248,
|
| 1061 |
+
"learning_rate": 5.208613930041323e-05,
|
| 1062 |
+
"loss": 4.1211,
|
| 1063 |
+
"step": 150
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.495049504950495,
|
| 1067 |
+
"grad_norm": 50.39912414550781,
|
| 1068 |
+
"learning_rate": 5.09608944176561e-05,
|
| 1069 |
+
"loss": 9.9336,
|
| 1070 |
+
"step": 151
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.504950495049505,
|
| 1074 |
+
"grad_norm": 2.4307775497436523,
|
| 1075 |
+
"learning_rate": 4.985162167051917e-05,
|
| 1076 |
+
"loss": 4.9141,
|
| 1077 |
+
"step": 152
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.5148514851485149,
|
| 1081 |
+
"grad_norm": 1.858076572418213,
|
| 1082 |
+
"learning_rate": 4.875862115593951e-05,
|
| 1083 |
+
"loss": 3.7559,
|
| 1084 |
+
"step": 153
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.5247524752475248,
|
| 1088 |
+
"grad_norm": 1.654653787612915,
|
| 1089 |
+
"learning_rate": 4.7682188568648294e-05,
|
| 1090 |
+
"loss": 3.8965,
|
| 1091 |
+
"step": 154
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.5346534653465347,
|
| 1095 |
+
"grad_norm": 1.9130183458328247,
|
| 1096 |
+
"learning_rate": 4.662261512117496e-05,
|
| 1097 |
+
"loss": 3.5098,
|
| 1098 |
+
"step": 155
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.5445544554455446,
|
| 1102 |
+
"grad_norm": 2.3735601902008057,
|
| 1103 |
+
"learning_rate": 4.558018746506396e-05,
|
| 1104 |
+
"loss": 3.4219,
|
| 1105 |
+
"step": 156
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.5544554455445545,
|
| 1109 |
+
"grad_norm": 1.6245256662368774,
|
| 1110 |
+
"learning_rate": 4.455518761332576e-05,
|
| 1111 |
+
"loss": 3.4375,
|
| 1112 |
+
"step": 157
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.5643564356435644,
|
| 1116 |
+
"grad_norm": 1.7158585786819458,
|
| 1117 |
+
"learning_rate": 4.35478928641423e-05,
|
| 1118 |
+
"loss": 4.0195,
|
| 1119 |
+
"step": 158
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.5742574257425743,
|
| 1123 |
+
"grad_norm": 1.537367343902588,
|
| 1124 |
+
"learning_rate": 4.25585757258483e-05,
|
| 1125 |
+
"loss": 3.1113,
|
| 1126 |
+
"step": 159
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.5841584158415842,
|
| 1130 |
+
"grad_norm": 2.29418683052063,
|
| 1131 |
+
"learning_rate": 4.158750384320811e-05,
|
| 1132 |
+
"loss": 3.9023,
|
| 1133 |
+
"step": 160
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.5940594059405941,
|
| 1137 |
+
"grad_norm": 14.955975532531738,
|
| 1138 |
+
"learning_rate": 4.063493992500865e-05,
|
| 1139 |
+
"loss": 7.5469,
|
| 1140 |
+
"step": 161
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.603960396039604,
|
| 1144 |
+
"grad_norm": 2.4816298484802246,
|
| 1145 |
+
"learning_rate": 3.9701141672987406e-05,
|
| 1146 |
+
"loss": 4.8594,
|
| 1147 |
+
"step": 162
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.613861386138614,
|
| 1151 |
+
"grad_norm": 1.8471182584762573,
|
| 1152 |
+
"learning_rate": 3.878636171211518e-05,
|
| 1153 |
+
"loss": 3.4258,
|
| 1154 |
+
"step": 163
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.6237623762376239,
|
| 1158 |
+
"grad_norm": 1.9999842643737793,
|
| 1159 |
+
"learning_rate": 3.789084752225219e-05,
|
| 1160 |
+
"loss": 4.6172,
|
| 1161 |
+
"step": 164
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.6336633663366338,
|
| 1165 |
+
"grad_norm": 1.5966260433197021,
|
| 1166 |
+
"learning_rate": 3.701484137119613e-05,
|
| 1167 |
+
"loss": 3.7656,
|
| 1168 |
+
"step": 165
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.6435643564356437,
|
| 1172 |
+
"grad_norm": 1.9665318727493286,
|
| 1173 |
+
"learning_rate": 3.615858024914048e-05,
|
| 1174 |
+
"loss": 3.8867,
|
| 1175 |
+
"step": 166
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.6534653465346536,
|
| 1179 |
+
"grad_norm": 39.52935791015625,
|
| 1180 |
+
"learning_rate": 3.532229580456006e-05,
|
| 1181 |
+
"loss": 7.5195,
|
| 1182 |
+
"step": 167
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.6633663366336635,
|
| 1186 |
+
"grad_norm": 2.001122236251831,
|
| 1187 |
+
"learning_rate": 3.450621428154235e-05,
|
| 1188 |
+
"loss": 4.2148,
|
| 1189 |
+
"step": 168
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.6732673267326734,
|
| 1193 |
+
"grad_norm": 1.9016386270523071,
|
| 1194 |
+
"learning_rate": 3.371055645858038e-05,
|
| 1195 |
+
"loss": 3.6035,
|
| 1196 |
+
"step": 169
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.6831683168316833,
|
| 1200 |
+
"grad_norm": 8.8970947265625,
|
| 1201 |
+
"learning_rate": 3.2935537588844645e-05,
|
| 1202 |
+
"loss": 5.6367,
|
| 1203 |
+
"step": 170
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.693069306930693,
|
| 1207 |
+
"grad_norm": 1.5331684350967407,
|
| 1208 |
+
"learning_rate": 3.218136734194936e-05,
|
| 1209 |
+
"loss": 4.3047,
|
| 1210 |
+
"step": 171
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.702970297029703,
|
| 1214 |
+
"grad_norm": 1.695820927619934,
|
| 1215 |
+
"learning_rate": 3.144824974722983e-05,
|
| 1216 |
+
"loss": 3.3164,
|
| 1217 |
+
"step": 172
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.7128712871287128,
|
| 1221 |
+
"grad_norm": 7.624035835266113,
|
| 1222 |
+
"learning_rate": 3.0736383138545086e-05,
|
| 1223 |
+
"loss": 3.7305,
|
| 1224 |
+
"step": 173
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.7227722772277227,
|
| 1228 |
+
"grad_norm": 1.5859265327453613,
|
| 1229 |
+
"learning_rate": 3.0045960100621918e-05,
|
| 1230 |
+
"loss": 3.2656,
|
| 1231 |
+
"step": 174
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.7326732673267327,
|
| 1235 |
+
"grad_norm": 1.5074691772460938,
|
| 1236 |
+
"learning_rate": 2.937716741695392e-05,
|
| 1237 |
+
"loss": 3.1797,
|
| 1238 |
+
"step": 175
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.7425742574257426,
|
| 1242 |
+
"grad_norm": 1.3923929929733276,
|
| 1243 |
+
"learning_rate": 2.873018601926994e-05,
|
| 1244 |
+
"loss": 3.1094,
|
| 1245 |
+
"step": 176
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.7524752475247525,
|
| 1249 |
+
"grad_norm": 1.4183502197265625,
|
| 1250 |
+
"learning_rate": 2.8105190938585885e-05,
|
| 1251 |
+
"loss": 3.1641,
|
| 1252 |
+
"step": 177
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.7623762376237624,
|
| 1256 |
+
"grad_norm": 1.5268654823303223,
|
| 1257 |
+
"learning_rate": 2.7502351257852678e-05,
|
| 1258 |
+
"loss": 2.7832,
|
| 1259 |
+
"step": 178
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.7722772277227723,
|
| 1263 |
+
"grad_norm": 1.5342729091644287,
|
| 1264 |
+
"learning_rate": 2.692183006621338e-05,
|
| 1265 |
+
"loss": 2.8652,
|
| 1266 |
+
"step": 179
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.7821782178217822,
|
| 1270 |
+
"grad_norm": 1.6859102249145508,
|
| 1271 |
+
"learning_rate": 2.636378441488197e-05,
|
| 1272 |
+
"loss": 3.1641,
|
| 1273 |
+
"step": 180
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.7920792079207921,
|
| 1277 |
+
"grad_norm": 1.5989638566970825,
|
| 1278 |
+
"learning_rate": 2.5828365274655457e-05,
|
| 1279 |
+
"loss": 3.0234,
|
| 1280 |
+
"step": 181
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.801980198019802,
|
| 1284 |
+
"grad_norm": 1.5343683958053589,
|
| 1285 |
+
"learning_rate": 2.5315717495071078e-05,
|
| 1286 |
+
"loss": 2.5156,
|
| 1287 |
+
"step": 182
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.811881188118812,
|
| 1291 |
+
"grad_norm": 1.508675456047058,
|
| 1292 |
+
"learning_rate": 2.4825979765219392e-05,
|
| 1293 |
+
"loss": 2.6621,
|
| 1294 |
+
"step": 183
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.8217821782178216,
|
| 1298 |
+
"grad_norm": 19.975343704223633,
|
| 1299 |
+
"learning_rate": 2.4359284576224078e-05,
|
| 1300 |
+
"loss": 7.1133,
|
| 1301 |
+
"step": 184
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.8316831683168315,
|
| 1305 |
+
"grad_norm": 3.3649535179138184,
|
| 1306 |
+
"learning_rate": 2.3915758185398423e-05,
|
| 1307 |
+
"loss": 4.6992,
|
| 1308 |
+
"step": 185
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.8415841584158414,
|
| 1312 |
+
"grad_norm": 2.1585795879364014,
|
| 1313 |
+
"learning_rate": 2.3495520582088455e-05,
|
| 1314 |
+
"loss": 3.5879,
|
| 1315 |
+
"step": 186
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 1.8514851485148514,
|
| 1319 |
+
"grad_norm": 2.5024328231811523,
|
| 1320 |
+
"learning_rate": 2.3098685455211446e-05,
|
| 1321 |
+
"loss": 4.875,
|
| 1322 |
+
"step": 187
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.8613861386138613,
|
| 1326 |
+
"grad_norm": 15.675300598144531,
|
| 1327 |
+
"learning_rate": 2.272536016249926e-05,
|
| 1328 |
+
"loss": 7.0469,
|
| 1329 |
+
"step": 188
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.8712871287128712,
|
| 1333 |
+
"grad_norm": 2.0795493125915527,
|
| 1334 |
+
"learning_rate": 2.2375645701454248e-05,
|
| 1335 |
+
"loss": 4.3086,
|
| 1336 |
+
"step": 189
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.881188118811881,
|
| 1340 |
+
"grad_norm": 1.4968867301940918,
|
| 1341 |
+
"learning_rate": 2.2049636682025957e-05,
|
| 1342 |
+
"loss": 3.1797,
|
| 1343 |
+
"step": 190
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.891089108910891,
|
| 1347 |
+
"grad_norm": 1.6626455783843994,
|
| 1348 |
+
"learning_rate": 2.174742130101581e-05,
|
| 1349 |
+
"loss": 3.2617,
|
| 1350 |
+
"step": 191
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.900990099009901,
|
| 1354 |
+
"grad_norm": 1.4873976707458496,
|
| 1355 |
+
"learning_rate": 2.1469081318216833e-05,
|
| 1356 |
+
"loss": 3.0488,
|
| 1357 |
+
"step": 192
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.9108910891089108,
|
| 1361 |
+
"grad_norm": 1.8592286109924316,
|
| 1362 |
+
"learning_rate": 2.121469203429473e-05,
|
| 1363 |
+
"loss": 3.2988,
|
| 1364 |
+
"step": 193
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.9207920792079207,
|
| 1368 |
+
"grad_norm": 1.742360234260559,
|
| 1369 |
+
"learning_rate": 2.0984322270416487e-05,
|
| 1370 |
+
"loss": 3.0312,
|
| 1371 |
+
"step": 194
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.9306930693069306,
|
| 1375 |
+
"grad_norm": 1.4714621305465698,
|
| 1376 |
+
"learning_rate": 2.077803434963179e-05,
|
| 1377 |
+
"loss": 2.6895,
|
| 1378 |
+
"step": 195
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.9405940594059405,
|
| 1382 |
+
"grad_norm": 1.268083095550537,
|
| 1383 |
+
"learning_rate": 2.059588408001252e-05,
|
| 1384 |
+
"loss": 2.5215,
|
| 1385 |
+
"step": 196
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.9504950495049505,
|
| 1389 |
+
"grad_norm": 1.3318591117858887,
|
| 1390 |
+
"learning_rate": 2.0437920739554686e-05,
|
| 1391 |
+
"loss": 2.543,
|
| 1392 |
+
"step": 197
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.9603960396039604,
|
| 1396 |
+
"grad_norm": 1.3971670866012573,
|
| 1397 |
+
"learning_rate": 2.0304187062847038e-05,
|
| 1398 |
+
"loss": 2.6191,
|
| 1399 |
+
"step": 198
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.9702970297029703,
|
| 1403 |
+
"grad_norm": 1.3031758069992065,
|
| 1404 |
+
"learning_rate": 2.0194719229509842e-05,
|
| 1405 |
+
"loss": 2.418,
|
| 1406 |
+
"step": 199
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.9801980198019802,
|
| 1410 |
+
"grad_norm": 1.3859241008758545,
|
| 1411 |
+
"learning_rate": 2.0109546854407064e-05,
|
| 1412 |
+
"loss": 2.5918,
|
| 1413 |
+
"step": 200
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.99009900990099,
|
| 1417 |
+
"grad_norm": 1.3760048151016235,
|
| 1418 |
+
"learning_rate": 2.0048692979634493e-05,
|
| 1419 |
+
"loss": 2.6914,
|
| 1420 |
+
"step": 201
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.0,
|
| 1424 |
+
"grad_norm": 1.2137415409088135,
|
| 1425 |
+
"learning_rate": 2.0012174068286065e-05,
|
| 1426 |
+
"loss": 1.6016,
|
| 1427 |
+
"step": 202
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 2.0,
|
| 1431 |
+
"eval_loss": 2.703822612762451,
|
| 1432 |
+
"eval_runtime": 12.5311,
|
| 1433 |
+
"eval_samples_per_second": 4.309,
|
| 1434 |
+
"eval_steps_per_second": 0.559,
|
| 1435 |
+
"step": 202
|
| 1436 |
+
}
|
| 1437 |
+
],
|
| 1438 |
+
"logging_steps": 1.0,
|
| 1439 |
+
"max_steps": 202,
|
| 1440 |
+
"num_input_tokens_seen": 0,
|
| 1441 |
+
"num_train_epochs": 2,
|
| 1442 |
+
"save_steps": 101,
|
| 1443 |
+
"stateful_callbacks": {
|
| 1444 |
+
"TrainerControl": {
|
| 1445 |
+
"args": {
|
| 1446 |
+
"should_epoch_stop": false,
|
| 1447 |
+
"should_evaluate": false,
|
| 1448 |
+
"should_log": false,
|
| 1449 |
+
"should_save": true,
|
| 1450 |
+
"should_training_stop": true
|
| 1451 |
+
},
|
| 1452 |
+
"attributes": {}
|
| 1453 |
+
}
|
| 1454 |
+
},
|
| 1455 |
+
"total_flos": 3.5479892660867564e+18,
|
| 1456 |
+
"train_batch_size": 1,
|
| 1457 |
+
"trial_name": null,
|
| 1458 |
+
"trial_params": null
|
| 1459 |
+
}
|