Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/.launching +1 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/all_results.json +8 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/chat_template.jinja +1 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/config.json +178 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/generation_config.json +13 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/model-00001-of-00002.safetensors +3 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/model-00002-of-00002.safetensors +3 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/model.safetensors.index.json +0 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/processor_config.json +75 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer.json +3 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer_config.json +56 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/train_results.json +8 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/trainer_log.jsonl +13 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/trainer_state.json +1016 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/training_args.bin +3 -0
- g2_6_oldcode_review_newcode_v4__edit/1000M/training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -84,3 +84,4 @@ g2_5_plan_newcode__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge
|
|
| 84 |
g2_5_plan_newcode__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 85 |
g2_6_oldcode_review_newcode_v4/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 86 |
g2_5_plan_newcode__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 84 |
g2_5_plan_newcode__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 85 |
g2_6_oldcode_review_newcode_v4/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 86 |
g2_5_plan_newcode__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
g2_6_oldcode_review_newcode_v4__edit/1000M/.launching
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
8830938 2026-09-21 07:44:22 x4703c4s4b0n0 1272->1399
|
g2_6_oldcode_review_newcode_v4__edit/1000M/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.7750692520775623,
|
| 3 |
+
"total_flos": 9636328589230080.0,
|
| 4 |
+
"train_loss": 0.046684147887267415,
|
| 5 |
+
"train_runtime": 5206.8179,
|
| 6 |
+
"train_samples_per_second": 25.794,
|
| 7 |
+
"train_steps_per_second": 0.269
|
| 8 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '<eos>' }}{% endif %}{% endfor %}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/config.json
ADDED
|
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": null,
|
| 6 |
+
"audio_token_id": 258881,
|
| 7 |
+
"boa_token_id": 256000,
|
| 8 |
+
"boi_token_id": 255999,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eoa_token_id": 258883,
|
| 12 |
+
"eoa_token_index": 258883,
|
| 13 |
+
"eoi_token_id": 258882,
|
| 14 |
+
"eos_token_id": 1,
|
| 15 |
+
"hidden_size": 5376,
|
| 16 |
+
"image_token_id": 258880,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"model_type": "gemma4",
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"text_config": {
|
| 21 |
+
"attention_bias": false,
|
| 22 |
+
"attention_dropout": 0.0,
|
| 23 |
+
"attention_k_eq_v": true,
|
| 24 |
+
"bos_token_id": 2,
|
| 25 |
+
"dtype": "bfloat16",
|
| 26 |
+
"enable_moe_block": false,
|
| 27 |
+
"eos_token_id": 1,
|
| 28 |
+
"expert_intermediate_size": null,
|
| 29 |
+
"final_logit_softcapping": 30.0,
|
| 30 |
+
"global_head_dim": 512,
|
| 31 |
+
"head_dim": 256,
|
| 32 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 33 |
+
"hidden_size": 5376,
|
| 34 |
+
"hidden_size_per_layer_input": 0,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 21504,
|
| 37 |
+
"layer_types": [
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"sliding_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"sliding_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"sliding_attention",
|
| 72 |
+
"sliding_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"sliding_attention",
|
| 75 |
+
"sliding_attention",
|
| 76 |
+
"sliding_attention",
|
| 77 |
+
"sliding_attention",
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"sliding_attention",
|
| 81 |
+
"sliding_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"sliding_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"sliding_attention",
|
| 87 |
+
"sliding_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"sliding_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"full_attention",
|
| 92 |
+
"sliding_attention",
|
| 93 |
+
"sliding_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"sliding_attention",
|
| 96 |
+
"sliding_attention",
|
| 97 |
+
"full_attention"
|
| 98 |
+
],
|
| 99 |
+
"max_position_embeddings": 262144,
|
| 100 |
+
"model_type": "gemma4_text",
|
| 101 |
+
"moe_intermediate_size": null,
|
| 102 |
+
"num_attention_heads": 32,
|
| 103 |
+
"num_experts": null,
|
| 104 |
+
"num_global_key_value_heads": 4,
|
| 105 |
+
"num_hidden_layers": 60,
|
| 106 |
+
"num_key_value_heads": 16,
|
| 107 |
+
"num_kv_shared_layers": 0,
|
| 108 |
+
"pad_token_id": 0,
|
| 109 |
+
"rms_norm_eps": 1e-06,
|
| 110 |
+
"rope_parameters": {
|
| 111 |
+
"full_attention": {
|
| 112 |
+
"partial_rotary_factor": 0.25,
|
| 113 |
+
"rope_theta": 1000000.0,
|
| 114 |
+
"rope_type": "proportional"
|
| 115 |
+
},
|
| 116 |
+
"sliding_attention": {
|
| 117 |
+
"rope_theta": 10000.0,
|
| 118 |
+
"rope_type": "default"
|
| 119 |
+
}
|
| 120 |
+
},
|
| 121 |
+
"sliding_window": 1024,
|
| 122 |
+
"tie_word_embeddings": true,
|
| 123 |
+
"top_k_experts": null,
|
| 124 |
+
"use_bidirectional_attention": "vision",
|
| 125 |
+
"use_cache": false,
|
| 126 |
+
"use_double_wide_mlp": false,
|
| 127 |
+
"vocab_size": 262144,
|
| 128 |
+
"vocab_size_per_layer_input": 262144
|
| 129 |
+
},
|
| 130 |
+
"tie_word_embeddings": true,
|
| 131 |
+
"transformers_version": "5.10.0",
|
| 132 |
+
"use_cache": false,
|
| 133 |
+
"video_token_id": 258884,
|
| 134 |
+
"vision_config": {
|
| 135 |
+
"_name_or_path": "",
|
| 136 |
+
"architectures": null,
|
| 137 |
+
"attention_bias": false,
|
| 138 |
+
"attention_dropout": 0.0,
|
| 139 |
+
"chunk_size_feed_forward": 0,
|
| 140 |
+
"default_output_length": 280,
|
| 141 |
+
"dtype": "bfloat16",
|
| 142 |
+
"global_head_dim": 72,
|
| 143 |
+
"head_dim": 72,
|
| 144 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 145 |
+
"hidden_size": 1152,
|
| 146 |
+
"id2label": {
|
| 147 |
+
"0": "LABEL_0",
|
| 148 |
+
"1": "LABEL_1"
|
| 149 |
+
},
|
| 150 |
+
"initializer_range": 0.02,
|
| 151 |
+
"intermediate_size": 4304,
|
| 152 |
+
"is_encoder_decoder": false,
|
| 153 |
+
"label2id": {
|
| 154 |
+
"LABEL_0": 0,
|
| 155 |
+
"LABEL_1": 1
|
| 156 |
+
},
|
| 157 |
+
"max_position_embeddings": 131072,
|
| 158 |
+
"model_type": "gemma4_vision",
|
| 159 |
+
"num_attention_heads": 16,
|
| 160 |
+
"num_hidden_layers": 27,
|
| 161 |
+
"num_key_value_heads": 16,
|
| 162 |
+
"output_attentions": false,
|
| 163 |
+
"output_hidden_states": false,
|
| 164 |
+
"patch_size": 16,
|
| 165 |
+
"pooling_kernel_size": 3,
|
| 166 |
+
"position_embedding_size": 10240,
|
| 167 |
+
"problem_type": null,
|
| 168 |
+
"return_dict": true,
|
| 169 |
+
"rms_norm_eps": 1e-06,
|
| 170 |
+
"rope_parameters": {
|
| 171 |
+
"rope_theta": 100.0,
|
| 172 |
+
"rope_type": "default"
|
| 173 |
+
},
|
| 174 |
+
"standardize": true,
|
| 175 |
+
"use_clipped_linears": false
|
| 176 |
+
},
|
| 177 |
+
"vision_soft_tokens_per_image": 280
|
| 178 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
1
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.10.0"
|
| 13 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5ff0fc44e089d274f54a0f132c3f65c4df2c3df0403bdee8e847282ab49231d
|
| 3 |
+
size 49923154850
|
g2_6_oldcode_review_newcode_v4__edit/1000M/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:106add0297d1ffc27652cd0726b101a168457d1ce2b8b1fc94852462cb14c95d
|
| 3 |
+
size 12623183414
|
g2_6_oldcode_review_newcode_v4__edit/1000M/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
g2_6_oldcode_review_newcode_v4__edit/1000M/processor_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 7 |
+
"feature_size": 128,
|
| 8 |
+
"fft_length": 512,
|
| 9 |
+
"fft_overdrive": false,
|
| 10 |
+
"frame_length": 320,
|
| 11 |
+
"hop_length": 160,
|
| 12 |
+
"input_scale_factor": 1.0,
|
| 13 |
+
"max_frequency": 8000.0,
|
| 14 |
+
"mel_floor": 0.001,
|
| 15 |
+
"min_frequency": 0.0,
|
| 16 |
+
"padding_side": "right",
|
| 17 |
+
"padding_value": 0.0,
|
| 18 |
+
"per_bin_mean": null,
|
| 19 |
+
"per_bin_stddev": null,
|
| 20 |
+
"preemphasis": 0.0,
|
| 21 |
+
"preemphasis_htk_flavor": true,
|
| 22 |
+
"return_attention_mask": true,
|
| 23 |
+
"sampling_rate": 16000
|
| 24 |
+
},
|
| 25 |
+
"image_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": false,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"do_resize": true,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0
|
| 34 |
+
],
|
| 35 |
+
"image_processor_type": "Gemma4ImageProcessor",
|
| 36 |
+
"image_seq_length": 280,
|
| 37 |
+
"image_std": [
|
| 38 |
+
1.0,
|
| 39 |
+
1.0,
|
| 40 |
+
1.0
|
| 41 |
+
],
|
| 42 |
+
"max_soft_tokens": 280,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pooling_kernel_size": 3,
|
| 45 |
+
"resample": 3,
|
| 46 |
+
"rescale_factor": 0.00392156862745098
|
| 47 |
+
},
|
| 48 |
+
"image_seq_length": 280,
|
| 49 |
+
"processor_class": "Gemma4Processor",
|
| 50 |
+
"video_processor": {
|
| 51 |
+
"do_convert_rgb": true,
|
| 52 |
+
"do_normalize": true,
|
| 53 |
+
"do_rescale": true,
|
| 54 |
+
"do_resize": true,
|
| 55 |
+
"do_sample_frames": true,
|
| 56 |
+
"image_mean": [
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0
|
| 60 |
+
],
|
| 61 |
+
"image_std": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"max_soft_tokens": 70,
|
| 67 |
+
"num_frames": 32,
|
| 68 |
+
"patch_size": 16,
|
| 69 |
+
"pooling_kernel_size": 3,
|
| 70 |
+
"resample": 3,
|
| 71 |
+
"rescale_factor": 0.00392156862745098,
|
| 72 |
+
"return_metadata": false,
|
| 73 |
+
"video_processor_type": "Gemma4VideoProcessor"
|
| 74 |
+
}
|
| 75 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
|
| 3 |
+
size 32170070
|
g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": true,
|
| 21 |
+
"local_files_only": true,
|
| 22 |
+
"mask_token": "<mask>",
|
| 23 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 24 |
+
"model_specific_special_tokens": {
|
| 25 |
+
"audio_token": "<|audio|>",
|
| 26 |
+
"boa_token": "<|audio>",
|
| 27 |
+
"boi_token": "<|image>",
|
| 28 |
+
"eoa_token": "<audio|>",
|
| 29 |
+
"eoc_token": "<channel|>",
|
| 30 |
+
"eoi_token": "<image|>",
|
| 31 |
+
"eot_token": "<turn|>",
|
| 32 |
+
"escape_token": "<|\"|>",
|
| 33 |
+
"etc_token": "<tool_call|>",
|
| 34 |
+
"etd_token": "<tool|>",
|
| 35 |
+
"etr_token": "<tool_response|>",
|
| 36 |
+
"image_token": "<|image|>",
|
| 37 |
+
"soc_token": "<|channel>",
|
| 38 |
+
"sot_token": "<|turn>",
|
| 39 |
+
"stc_token": "<|tool_call>",
|
| 40 |
+
"std_token": "<|tool>",
|
| 41 |
+
"str_token": "<|tool_response>",
|
| 42 |
+
"think_token": "<|think|>"
|
| 43 |
+
},
|
| 44 |
+
"pad_token": "<pad>",
|
| 45 |
+
"padding_side": "right",
|
| 46 |
+
"processor_class": "Gemma4Processor",
|
| 47 |
+
"soc_token": "<|channel>",
|
| 48 |
+
"sot_token": "<|turn>",
|
| 49 |
+
"split_special_tokens": false,
|
| 50 |
+
"stc_token": "<|tool_call>",
|
| 51 |
+
"std_token": "<|tool>",
|
| 52 |
+
"str_token": "<|tool_response>",
|
| 53 |
+
"think_token": "<|think|>",
|
| 54 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.7750692520775623,
|
| 3 |
+
"total_flos": 9636328589230080.0,
|
| 4 |
+
"train_loss": 0.046684147887267415,
|
| 5 |
+
"train_runtime": 5206.8179,
|
| 6 |
+
"train_samples_per_second": 25.794,
|
| 7 |
+
"train_steps_per_second": 0.269
|
| 8 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1280, "total_steps": 1399, "loss": 0.5259709358215332, "lr": 1.985120236000677e-05, "epoch": 0.7091412742382271, "percentage": 91.49, "elapsed_time": "0:05:35", "remaining_time": "0:00:31"}
|
| 2 |
+
{"current_steps": 1290, "total_steps": 1399, "loss": 0.5255245685577392, "lr": 1.9133090868227833e-05, "epoch": 0.7146814404432132, "percentage": 92.21, "elapsed_time": "0:12:18", "remaining_time": "0:01:02"}
|
| 3 |
+
{"current_steps": 1300, "total_steps": 1399, "loss": 0.5152856826782226, "lr": 1.786199834829156e-05, "epoch": 0.7202216066481995, "percentage": 92.92, "elapsed_time": "0:19:02", "remaining_time": "0:01:26"}
|
| 4 |
+
{"current_steps": 1310, "total_steps": 1399, "loss": 0.5231216430664063, "lr": 1.6115309256519543e-05, "epoch": 0.7257617728531855, "percentage": 93.64, "elapsed_time": "0:25:44", "remaining_time": "0:01:44"}
|
| 5 |
+
{"current_steps": 1320, "total_steps": 1399, "loss": 0.5098329544067383, "lr": 1.399936249712973e-05, "epoch": 0.7313019390581718, "percentage": 94.35, "elapsed_time": "0:32:28", "remaining_time": "0:01:56"}
|
| 6 |
+
{"current_steps": 1330, "total_steps": 1399, "loss": 0.5115524291992187, "lr": 1.1642977480993187e-05, "epoch": 0.7368421052631579, "percentage": 95.07, "elapsed_time": "0:39:13", "remaining_time": "0:02:02"}
|
| 7 |
+
{"current_steps": 1340, "total_steps": 1399, "loss": 0.516216230392456, "lr": 9.189611565067083e-06, "epoch": 0.7423822714681441, "percentage": 95.78, "elapsed_time": "0:45:58", "remaining_time": "0:02:01"}
|
| 8 |
+
{"current_steps": 1350, "total_steps": 1399, "loss": 0.5149363994598388, "lr": 6.788626329711741e-06, "epoch": 0.7479224376731302, "percentage": 96.5, "elapsed_time": "0:52:41", "remaining_time": "0:01:54"}
|
| 9 |
+
{"current_steps": 1360, "total_steps": 1399, "loss": 0.5075156211853027, "lr": 4.5861944052904325e-06, "epoch": 0.7534626038781164, "percentage": 97.21, "elapsed_time": "0:59:25", "remaining_time": "0:01:42"}
|
| 10 |
+
{"current_steps": 1370, "total_steps": 1399, "loss": 0.4956242084503174, "lr": 2.7164004429072312e-06, "epoch": 0.7590027700831025, "percentage": 97.93, "elapsed_time": "1:06:10", "remaining_time": "0:01:24"}
|
| 11 |
+
{"current_steps": 1380, "total_steps": 1399, "loss": 0.5104885101318359, "lr": 1.2930780045908777e-06, "epoch": 0.7645429362880887, "percentage": 98.64, "elapsed_time": "1:12:54", "remaining_time": "0:01:00"}
|
| 12 |
+
{"current_steps": 1390, "total_steps": 1399, "loss": 0.5073337554931641, "lr": 4.028793452574461e-07, "epoch": 0.7700831024930748, "percentage": 99.36, "elapsed_time": "1:19:38", "remaining_time": "0:00:30"}
|
| 13 |
+
{"current_steps": 1399, "total_steps": 1399, "epoch": 0.7750692520775623, "percentage": 100.0, "elapsed_time": "1:26:46", "remaining_time": "0:00:00"}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/trainer_state.json
ADDED
|
@@ -0,0 +1,1016 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7750692520775623,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1399,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00554016620498615,
|
| 14 |
+
"grad_norm": 361.42560871926736,
|
| 15 |
+
"learning_rate": 8.240909090909092e-06,
|
| 16 |
+
"loss": 1.3333003044128418,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0110803324099723,
|
| 21 |
+
"grad_norm": 99.91973972164922,
|
| 22 |
+
"learning_rate": 1.728636363636364e-05,
|
| 23 |
+
"loss": 0.718450927734375,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01662049861495845,
|
| 28 |
+
"grad_norm": 33.06083131447389,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 0.6590091228485108,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0221606648199446,
|
| 35 |
+
"grad_norm": 7.927297295567435,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 0.6481295585632324,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.027700831024930747,
|
| 42 |
+
"grad_norm": 3.756589251827393,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 0.6498578071594239,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0332409972299169,
|
| 49 |
+
"grad_norm": 18.829804528668515,
|
| 50 |
+
"learning_rate": 2e-05,
|
| 51 |
+
"loss": 0.6214908872331891,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.038781163434903045,
|
| 56 |
+
"grad_norm": 19.43873982641671,
|
| 57 |
+
"learning_rate": 2e-05,
|
| 58 |
+
"loss": 0.6026109218597412,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0443213296398892,
|
| 63 |
+
"grad_norm": 43.33178758215569,
|
| 64 |
+
"learning_rate": 2e-05,
|
| 65 |
+
"loss": 0.5805820465087891,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04986149584487535,
|
| 70 |
+
"grad_norm": 53.11917253584653,
|
| 71 |
+
"learning_rate": 2e-05,
|
| 72 |
+
"loss": 0.586087703704834,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.055401662049861494,
|
| 77 |
+
"grad_norm": 20.791618692952035,
|
| 78 |
+
"learning_rate": 2e-05,
|
| 79 |
+
"loss": 0.5829347133636474,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.060941828254847646,
|
| 84 |
+
"grad_norm": 3.137732044625462,
|
| 85 |
+
"learning_rate": 2e-05,
|
| 86 |
+
"loss": 0.6291256546974182,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0664819944598338,
|
| 91 |
+
"grad_norm": 3.278834647318204,
|
| 92 |
+
"learning_rate": 2e-05,
|
| 93 |
+
"loss": 0.6034554481506348,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.07202216066481995,
|
| 98 |
+
"grad_norm": 3.1342104160526962,
|
| 99 |
+
"learning_rate": 2e-05,
|
| 100 |
+
"loss": 0.6232475280761719,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.07756232686980609,
|
| 105 |
+
"grad_norm": 24.31633537597729,
|
| 106 |
+
"learning_rate": 2e-05,
|
| 107 |
+
"loss": 0.5859569072723388,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08310249307479224,
|
| 112 |
+
"grad_norm": 5.272421501572288,
|
| 113 |
+
"learning_rate": 2e-05,
|
| 114 |
+
"loss": 0.5842217922210693,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0886426592797784,
|
| 119 |
+
"grad_norm": 11.159290213110678,
|
| 120 |
+
"learning_rate": 2e-05,
|
| 121 |
+
"loss": 0.5758800506591797,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.09418282548476455,
|
| 126 |
+
"grad_norm": 20.01184830036414,
|
| 127 |
+
"learning_rate": 2e-05,
|
| 128 |
+
"loss": 0.5838713645935059,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0997229916897507,
|
| 133 |
+
"grad_norm": 16.58050497141215,
|
| 134 |
+
"learning_rate": 2e-05,
|
| 135 |
+
"loss": 0.5738828182220459,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.10526315789473684,
|
| 140 |
+
"grad_norm": 10.400078165704427,
|
| 141 |
+
"learning_rate": 2e-05,
|
| 142 |
+
"loss": 0.5794562816619873,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.11080332409972299,
|
| 147 |
+
"grad_norm": 8.06444691789255,
|
| 148 |
+
"learning_rate": 2e-05,
|
| 149 |
+
"loss": 0.5948227882385254,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.11634349030470914,
|
| 154 |
+
"grad_norm": 88.32068363221457,
|
| 155 |
+
"learning_rate": 2e-05,
|
| 156 |
+
"loss": 0.5965998649597168,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.12188365650969529,
|
| 161 |
+
"grad_norm": 96.5756379849439,
|
| 162 |
+
"learning_rate": 2e-05,
|
| 163 |
+
"loss": 0.5679566860198975,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.12742382271468145,
|
| 168 |
+
"grad_norm": 2.8117461506508032,
|
| 169 |
+
"learning_rate": 2e-05,
|
| 170 |
+
"loss": 0.5731313705444336,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1329639889196676,
|
| 175 |
+
"grad_norm": 2.2385395151323175,
|
| 176 |
+
"learning_rate": 2e-05,
|
| 177 |
+
"loss": 0.5875983238220215,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.13850415512465375,
|
| 182 |
+
"grad_norm": 6.632728152974986,
|
| 183 |
+
"learning_rate": 2e-05,
|
| 184 |
+
"loss": 0.577367115020752,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1440443213296399,
|
| 189 |
+
"grad_norm": 3.957982727267163,
|
| 190 |
+
"learning_rate": 2e-05,
|
| 191 |
+
"loss": 0.5877696990966796,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.14958448753462603,
|
| 196 |
+
"grad_norm": 1.5280288384472618,
|
| 197 |
+
"learning_rate": 2e-05,
|
| 198 |
+
"loss": 0.5691342830657959,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.15512465373961218,
|
| 203 |
+
"grad_norm": 8.956836614764308,
|
| 204 |
+
"learning_rate": 2e-05,
|
| 205 |
+
"loss": 0.5635541439056396,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.16066481994459833,
|
| 210 |
+
"grad_norm": 4.642126259025987,
|
| 211 |
+
"learning_rate": 2e-05,
|
| 212 |
+
"loss": 0.5634446620941163,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16620498614958448,
|
| 217 |
+
"grad_norm": 15.223697629137437,
|
| 218 |
+
"learning_rate": 2e-05,
|
| 219 |
+
"loss": 0.5600797176361084,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.17174515235457063,
|
| 224 |
+
"grad_norm": 1.5407989885892268,
|
| 225 |
+
"learning_rate": 2e-05,
|
| 226 |
+
"loss": 0.5590239524841308,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.1772853185595568,
|
| 231 |
+
"grad_norm": 6.022513614533874,
|
| 232 |
+
"learning_rate": 2e-05,
|
| 233 |
+
"loss": 0.5498495101928711,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.18282548476454294,
|
| 238 |
+
"grad_norm": 3.2441584356904256,
|
| 239 |
+
"learning_rate": 2e-05,
|
| 240 |
+
"loss": 0.5617608547210693,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1883656509695291,
|
| 245 |
+
"grad_norm": 2.8382749386696466,
|
| 246 |
+
"learning_rate": 2e-05,
|
| 247 |
+
"loss": 0.5503531455993652,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.19390581717451524,
|
| 252 |
+
"grad_norm": 3.1121116046762,
|
| 253 |
+
"learning_rate": 2e-05,
|
| 254 |
+
"loss": 0.557097339630127,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1994459833795014,
|
| 259 |
+
"grad_norm": 2.6354401620694037,
|
| 260 |
+
"learning_rate": 2e-05,
|
| 261 |
+
"loss": 0.5612289428710937,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.20498614958448755,
|
| 266 |
+
"grad_norm": 9.288121710804653,
|
| 267 |
+
"learning_rate": 2e-05,
|
| 268 |
+
"loss": 0.5653853416442871,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.21052631578947367,
|
| 273 |
+
"grad_norm": 3.284763946756673,
|
| 274 |
+
"learning_rate": 2e-05,
|
| 275 |
+
"loss": 0.5670746697319878,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.21606648199445982,
|
| 280 |
+
"grad_norm": 4.620360240410298,
|
| 281 |
+
"learning_rate": 2e-05,
|
| 282 |
+
"loss": 0.5685059547424316,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.22160664819944598,
|
| 287 |
+
"grad_norm": 1.7752940145306941,
|
| 288 |
+
"learning_rate": 2e-05,
|
| 289 |
+
"loss": 0.5873359203338623,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.22714681440443213,
|
| 294 |
+
"grad_norm": 4.167205012987901,
|
| 295 |
+
"learning_rate": 2e-05,
|
| 296 |
+
"loss": 0.565663480758667,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23268698060941828,
|
| 301 |
+
"grad_norm": 1.8626008415951418,
|
| 302 |
+
"learning_rate": 2e-05,
|
| 303 |
+
"loss": 0.5661162376403809,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.23822714681440443,
|
| 308 |
+
"grad_norm": 8.09784939714964,
|
| 309 |
+
"learning_rate": 2e-05,
|
| 310 |
+
"loss": 0.5523086786270142,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.24376731301939059,
|
| 315 |
+
"grad_norm": 9.378147846483317,
|
| 316 |
+
"learning_rate": 2e-05,
|
| 317 |
+
"loss": 0.5595599174499511,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.24930747922437674,
|
| 322 |
+
"grad_norm": 1.3394555569594102,
|
| 323 |
+
"learning_rate": 2e-05,
|
| 324 |
+
"loss": 0.5687192440032959,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2548476454293629,
|
| 329 |
+
"grad_norm": 0.7935611043328916,
|
| 330 |
+
"learning_rate": 2e-05,
|
| 331 |
+
"loss": 0.5708736419677735,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.26038781163434904,
|
| 336 |
+
"grad_norm": 2.353741465271429,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 0.5481966018676758,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2659279778393352,
|
| 343 |
+
"grad_norm": 2.23925267739689,
|
| 344 |
+
"learning_rate": 2e-05,
|
| 345 |
+
"loss": 0.5735257069269816,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.27146814404432135,
|
| 350 |
+
"grad_norm": 9.097330908915346,
|
| 351 |
+
"learning_rate": 2e-05,
|
| 352 |
+
"loss": 0.5498846054077149,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2770083102493075,
|
| 357 |
+
"grad_norm": 1.618323940947887,
|
| 358 |
+
"learning_rate": 2e-05,
|
| 359 |
+
"loss": 0.5361488342285157,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.28254847645429365,
|
| 364 |
+
"grad_norm": 2.4276909527456483,
|
| 365 |
+
"learning_rate": 2e-05,
|
| 366 |
+
"loss": 0.5541221618652343,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2880886426592798,
|
| 371 |
+
"grad_norm": 7.352677343052014,
|
| 372 |
+
"learning_rate": 2e-05,
|
| 373 |
+
"loss": 0.5514220237731934,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.29362880886426596,
|
| 378 |
+
"grad_norm": 3.417699112696068,
|
| 379 |
+
"learning_rate": 2e-05,
|
| 380 |
+
"loss": 0.5513012886047364,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29916897506925205,
|
| 385 |
+
"grad_norm": 6.529458326004469,
|
| 386 |
+
"learning_rate": 2e-05,
|
| 387 |
+
"loss": 0.5661341667175293,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3047091412742382,
|
| 392 |
+
"grad_norm": 4.404301608723522,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.5566968441009521,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.31024930747922436,
|
| 399 |
+
"grad_norm": 3.646881236809636,
|
| 400 |
+
"learning_rate": 2e-05,
|
| 401 |
+
"loss": 0.5547757625579834,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3157894736842105,
|
| 406 |
+
"grad_norm": 2.6116051789509616,
|
| 407 |
+
"learning_rate": 2e-05,
|
| 408 |
+
"loss": 0.5594514369964599,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.32132963988919666,
|
| 413 |
+
"grad_norm": 2.472867092545295,
|
| 414 |
+
"learning_rate": 2e-05,
|
| 415 |
+
"loss": 0.5515174865722656,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.3268698060941828,
|
| 420 |
+
"grad_norm": 10.557881816438439,
|
| 421 |
+
"learning_rate": 2e-05,
|
| 422 |
+
"loss": 0.5486064910888672,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.33240997229916897,
|
| 427 |
+
"grad_norm": 8.038407412616992,
|
| 428 |
+
"learning_rate": 2e-05,
|
| 429 |
+
"loss": 0.54862380027771,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.3379501385041551,
|
| 434 |
+
"grad_norm": 6.567158995765598,
|
| 435 |
+
"learning_rate": 2e-05,
|
| 436 |
+
"loss": 0.5547227382659912,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.34349030470914127,
|
| 441 |
+
"grad_norm": 8.553270331843141,
|
| 442 |
+
"learning_rate": 2e-05,
|
| 443 |
+
"loss": 0.5449647903442383,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3490304709141274,
|
| 448 |
+
"grad_norm": 1.9238451730746302,
|
| 449 |
+
"learning_rate": 2e-05,
|
| 450 |
+
"loss": 0.5453619003295899,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3545706371191136,
|
| 455 |
+
"grad_norm": 3.0211693244986164,
|
| 456 |
+
"learning_rate": 2e-05,
|
| 457 |
+
"loss": 0.544036865234375,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.3601108033240997,
|
| 462 |
+
"grad_norm": 1.05855047705091,
|
| 463 |
+
"learning_rate": 2e-05,
|
| 464 |
+
"loss": 0.5483445167541504,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3656509695290859,
|
| 469 |
+
"grad_norm": 1.109723616018037,
|
| 470 |
+
"learning_rate": 2e-05,
|
| 471 |
+
"loss": 0.5591496467590332,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.37119113573407203,
|
| 476 |
+
"grad_norm": 1.041944392332728,
|
| 477 |
+
"learning_rate": 2e-05,
|
| 478 |
+
"loss": 0.5499378204345703,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.3767313019390582,
|
| 483 |
+
"grad_norm": 18.16560560117969,
|
| 484 |
+
"learning_rate": 2e-05,
|
| 485 |
+
"loss": 0.5412339210510254,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.38227146814404434,
|
| 490 |
+
"grad_norm": 1.5903925966699077,
|
| 491 |
+
"learning_rate": 2e-05,
|
| 492 |
+
"loss": 0.5327317237854003,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.3878116343490305,
|
| 497 |
+
"grad_norm": 11.159770874372581,
|
| 498 |
+
"learning_rate": 2e-05,
|
| 499 |
+
"loss": 0.5293295860290528,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.39335180055401664,
|
| 504 |
+
"grad_norm": 1.8611602813833785,
|
| 505 |
+
"learning_rate": 2e-05,
|
| 506 |
+
"loss": 0.5447241783142089,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3988919667590028,
|
| 511 |
+
"grad_norm": 3.2241124128292937,
|
| 512 |
+
"learning_rate": 2e-05,
|
| 513 |
+
"loss": 0.5579368591308593,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.40443213296398894,
|
| 518 |
+
"grad_norm": 6.453259470953598,
|
| 519 |
+
"learning_rate": 2e-05,
|
| 520 |
+
"loss": 0.5301932334899903,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4099722991689751,
|
| 525 |
+
"grad_norm": 3.193813738680295,
|
| 526 |
+
"learning_rate": 2e-05,
|
| 527 |
+
"loss": 0.5321185111999511,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.4155124653739612,
|
| 532 |
+
"grad_norm": 1.4586936503497605,
|
| 533 |
+
"learning_rate": 2e-05,
|
| 534 |
+
"loss": 0.548641300201416,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.42105263157894735,
|
| 539 |
+
"grad_norm": 1.2638161114629207,
|
| 540 |
+
"learning_rate": 2e-05,
|
| 541 |
+
"loss": 0.5458884239196777,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4265927977839335,
|
| 546 |
+
"grad_norm": 0.746329211231126,
|
| 547 |
+
"learning_rate": 2e-05,
|
| 548 |
+
"loss": 0.5316133499145508,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.43213296398891965,
|
| 553 |
+
"grad_norm": 1.9919209646457547,
|
| 554 |
+
"learning_rate": 2e-05,
|
| 555 |
+
"loss": 0.5296189308166503,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4376731301939058,
|
| 560 |
+
"grad_norm": 0.7322853458584584,
|
| 561 |
+
"learning_rate": 2e-05,
|
| 562 |
+
"loss": 0.5344297409057617,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.44321329639889195,
|
| 567 |
+
"grad_norm": 1.523521473148984,
|
| 568 |
+
"learning_rate": 2e-05,
|
| 569 |
+
"loss": 0.5322764396667481,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4487534626038781,
|
| 574 |
+
"grad_norm": 1.371661451747301,
|
| 575 |
+
"learning_rate": 2e-05,
|
| 576 |
+
"loss": 0.5402735710144043,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.45429362880886426,
|
| 581 |
+
"grad_norm": 1.4924622388756141,
|
| 582 |
+
"learning_rate": 2e-05,
|
| 583 |
+
"loss": 0.544907522201538,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.4598337950138504,
|
| 588 |
+
"grad_norm": 0.8400172779449527,
|
| 589 |
+
"learning_rate": 2e-05,
|
| 590 |
+
"loss": 0.5371682167053222,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.46537396121883656,
|
| 595 |
+
"grad_norm": 2.44185569665917,
|
| 596 |
+
"learning_rate": 2e-05,
|
| 597 |
+
"loss": 0.5399882793426514,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.4709141274238227,
|
| 602 |
+
"grad_norm": 1.1617216840131024,
|
| 603 |
+
"learning_rate": 2e-05,
|
| 604 |
+
"loss": 0.5289427757263183,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.47645429362880887,
|
| 609 |
+
"grad_norm": 2.4113260324179873,
|
| 610 |
+
"learning_rate": 2e-05,
|
| 611 |
+
"loss": 0.5321330547332763,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.481994459833795,
|
| 616 |
+
"grad_norm": 2.1675963528169895,
|
| 617 |
+
"learning_rate": 2e-05,
|
| 618 |
+
"loss": 0.5365336418151856,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.48753462603878117,
|
| 623 |
+
"grad_norm": 1.1067488626866417,
|
| 624 |
+
"learning_rate": 2e-05,
|
| 625 |
+
"loss": 0.5228745460510253,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4930747922437673,
|
| 630 |
+
"grad_norm": 9.214206579117855,
|
| 631 |
+
"learning_rate": 2e-05,
|
| 632 |
+
"loss": 0.5376943111419678,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.4986149584487535,
|
| 637 |
+
"grad_norm": 0.9217178185105178,
|
| 638 |
+
"learning_rate": 2e-05,
|
| 639 |
+
"loss": 0.5398812770843506,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.5041551246537396,
|
| 644 |
+
"grad_norm": 1.5202882555009398,
|
| 645 |
+
"learning_rate": 2e-05,
|
| 646 |
+
"loss": 0.5405753983391656,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.5096952908587258,
|
| 651 |
+
"grad_norm": 1.3624746953945461,
|
| 652 |
+
"learning_rate": 2e-05,
|
| 653 |
+
"loss": 0.5215118885040283,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5152354570637119,
|
| 658 |
+
"grad_norm": 1.468051530734884,
|
| 659 |
+
"learning_rate": 2e-05,
|
| 660 |
+
"loss": 0.5330688953399658,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5207756232686981,
|
| 665 |
+
"grad_norm": 0.6091197053773216,
|
| 666 |
+
"learning_rate": 2e-05,
|
| 667 |
+
"loss": 0.5399077892303467,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5263157894736842,
|
| 672 |
+
"grad_norm": 1.2446392554025398,
|
| 673 |
+
"learning_rate": 2e-05,
|
| 674 |
+
"loss": 0.5226483821868897,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5318559556786704,
|
| 679 |
+
"grad_norm": 1.3333170937905074,
|
| 680 |
+
"learning_rate": 2e-05,
|
| 681 |
+
"loss": 0.5370802481969198,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5373961218836565,
|
| 686 |
+
"grad_norm": 2.5239220368329436,
|
| 687 |
+
"learning_rate": 2e-05,
|
| 688 |
+
"loss": 0.5348920822143555,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5429362880886427,
|
| 693 |
+
"grad_norm": 1.1103307501111455,
|
| 694 |
+
"learning_rate": 2e-05,
|
| 695 |
+
"loss": 0.536679744720459,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5484764542936288,
|
| 700 |
+
"grad_norm": 1.4234134316935145,
|
| 701 |
+
"learning_rate": 2e-05,
|
| 702 |
+
"loss": 0.5341271877288818,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.554016620498615,
|
| 707 |
+
"grad_norm": 0.657385178361092,
|
| 708 |
+
"learning_rate": 2e-05,
|
| 709 |
+
"loss": 0.5312092304229736,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.5595567867036011,
|
| 714 |
+
"grad_norm": 5.586381072347112,
|
| 715 |
+
"learning_rate": 2e-05,
|
| 716 |
+
"loss": 0.533313512802124,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.5650969529085873,
|
| 721 |
+
"grad_norm": 26.532954264260688,
|
| 722 |
+
"learning_rate": 2e-05,
|
| 723 |
+
"loss": 0.5271495819091797,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5706371191135734,
|
| 728 |
+
"grad_norm": 0.8355009713887606,
|
| 729 |
+
"learning_rate": 2e-05,
|
| 730 |
+
"loss": 0.5298872947692871,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.5761772853185596,
|
| 735 |
+
"grad_norm": 0.7053242510095774,
|
| 736 |
+
"learning_rate": 2e-05,
|
| 737 |
+
"loss": 0.5254716873168945,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5817174515235457,
|
| 742 |
+
"grad_norm": 1.0317787731083008,
|
| 743 |
+
"learning_rate": 2e-05,
|
| 744 |
+
"loss": 0.5318110942840576,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.5872576177285319,
|
| 749 |
+
"grad_norm": 3.0292105917719003,
|
| 750 |
+
"learning_rate": 2e-05,
|
| 751 |
+
"loss": 0.5320435047149659,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.592797783933518,
|
| 756 |
+
"grad_norm": 1.865023065329474,
|
| 757 |
+
"learning_rate": 2e-05,
|
| 758 |
+
"loss": 0.5249354839324951,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5983379501385041,
|
| 763 |
+
"grad_norm": 3.427675359623466,
|
| 764 |
+
"learning_rate": 2e-05,
|
| 765 |
+
"loss": 0.531105899810791,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.6038781163434903,
|
| 770 |
+
"grad_norm": 1.3628497297333686,
|
| 771 |
+
"learning_rate": 2e-05,
|
| 772 |
+
"loss": 0.5402257442474365,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.6094182825484764,
|
| 777 |
+
"grad_norm": 1.8426451501090597,
|
| 778 |
+
"learning_rate": 2e-05,
|
| 779 |
+
"loss": 0.539887523651123,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.6149584487534626,
|
| 784 |
+
"grad_norm": 1.170243706303257,
|
| 785 |
+
"learning_rate": 2e-05,
|
| 786 |
+
"loss": 0.5353090286254882,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.6204986149584487,
|
| 791 |
+
"grad_norm": 0.5021161044902409,
|
| 792 |
+
"learning_rate": 2e-05,
|
| 793 |
+
"loss": 0.5248796939849854,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6260387811634349,
|
| 798 |
+
"grad_norm": 2.271172085311588,
|
| 799 |
+
"learning_rate": 2e-05,
|
| 800 |
+
"loss": 0.5208919525146485,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.631578947368421,
|
| 805 |
+
"grad_norm": 5.5823011443927575,
|
| 806 |
+
"learning_rate": 2e-05,
|
| 807 |
+
"loss": 0.531984519958496,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.6371191135734072,
|
| 812 |
+
"grad_norm": 1.268564803015365,
|
| 813 |
+
"learning_rate": 2e-05,
|
| 814 |
+
"loss": 0.5312467098236084,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6426592797783933,
|
| 819 |
+
"grad_norm": 12.272935404030356,
|
| 820 |
+
"learning_rate": 2e-05,
|
| 821 |
+
"loss": 0.5241949081420898,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.6481994459833795,
|
| 826 |
+
"grad_norm": 0.6103799412211546,
|
| 827 |
+
"learning_rate": 2e-05,
|
| 828 |
+
"loss": 0.5365022182464599,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.6537396121883656,
|
| 833 |
+
"grad_norm": 0.497610129902319,
|
| 834 |
+
"learning_rate": 2e-05,
|
| 835 |
+
"loss": 0.5307685852050781,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.6592797783933518,
|
| 840 |
+
"grad_norm": 6.191615563127353,
|
| 841 |
+
"learning_rate": 2e-05,
|
| 842 |
+
"loss": 0.5221158981323242,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.6648199445983379,
|
| 847 |
+
"grad_norm": 0.7819711960434653,
|
| 848 |
+
"learning_rate": 2e-05,
|
| 849 |
+
"loss": 0.5262507915496826,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.6703601108033241,
|
| 854 |
+
"grad_norm": 0.5674701477238893,
|
| 855 |
+
"learning_rate": 2e-05,
|
| 856 |
+
"loss": 0.5228729248046875,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.6759002770083102,
|
| 861 |
+
"grad_norm": 0.5731314670135219,
|
| 862 |
+
"learning_rate": 2e-05,
|
| 863 |
+
"loss": 0.5164279937744141,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.6814404432132964,
|
| 868 |
+
"grad_norm": 0.7521721766043508,
|
| 869 |
+
"learning_rate": 2e-05,
|
| 870 |
+
"loss": 0.5093661308288574,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.6869806094182825,
|
| 875 |
+
"grad_norm": 2.4709990379065023,
|
| 876 |
+
"learning_rate": 2e-05,
|
| 877 |
+
"loss": 0.5287744998931885,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.6925207756232687,
|
| 882 |
+
"grad_norm": 1.1717920870935006,
|
| 883 |
+
"learning_rate": 2e-05,
|
| 884 |
+
"loss": 0.5240383148193359,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.6980609418282548,
|
| 889 |
+
"grad_norm": 1.5719444699244454,
|
| 890 |
+
"learning_rate": 2e-05,
|
| 891 |
+
"loss": 0.5136274337768555,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.703601108033241,
|
| 896 |
+
"grad_norm": 1.1272391560821318,
|
| 897 |
+
"learning_rate": 2e-05,
|
| 898 |
+
"loss": 0.5213839530944824,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.7091412742382271,
|
| 903 |
+
"grad_norm": 0.7602518508843568,
|
| 904 |
+
"learning_rate": 1.985120236000677e-05,
|
| 905 |
+
"loss": 0.5259709358215332,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7146814404432132,
|
| 910 |
+
"grad_norm": 0.6389045702909288,
|
| 911 |
+
"learning_rate": 1.9133090868227833e-05,
|
| 912 |
+
"loss": 0.5255245685577392,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.7202216066481995,
|
| 917 |
+
"grad_norm": 6.6615878780503515,
|
| 918 |
+
"learning_rate": 1.786199834829156e-05,
|
| 919 |
+
"loss": 0.5152856826782226,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.7257617728531855,
|
| 924 |
+
"grad_norm": 1.9102760689879745,
|
| 925 |
+
"learning_rate": 1.6115309256519543e-05,
|
| 926 |
+
"loss": 0.5231216430664063,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.7313019390581718,
|
| 931 |
+
"grad_norm": 2.078399110429618,
|
| 932 |
+
"learning_rate": 1.399936249712973e-05,
|
| 933 |
+
"loss": 0.5098329544067383,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.7368421052631579,
|
| 938 |
+
"grad_norm": 3.2261863741218977,
|
| 939 |
+
"learning_rate": 1.1642977480993187e-05,
|
| 940 |
+
"loss": 0.5115524291992187,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.7423822714681441,
|
| 945 |
+
"grad_norm": 0.5996996684689675,
|
| 946 |
+
"learning_rate": 9.189611565067083e-06,
|
| 947 |
+
"loss": 0.516216230392456,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.7479224376731302,
|
| 952 |
+
"grad_norm": 1.8815529893321612,
|
| 953 |
+
"learning_rate": 6.788626329711741e-06,
|
| 954 |
+
"loss": 0.5149363994598388,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.7534626038781164,
|
| 959 |
+
"grad_norm": 0.8832470337043532,
|
| 960 |
+
"learning_rate": 4.5861944052904325e-06,
|
| 961 |
+
"loss": 0.5075156211853027,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7590027700831025,
|
| 966 |
+
"grad_norm": 0.7803168696090564,
|
| 967 |
+
"learning_rate": 2.7164004429072312e-06,
|
| 968 |
+
"loss": 0.4956242084503174,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7645429362880887,
|
| 973 |
+
"grad_norm": 0.9108115175943265,
|
| 974 |
+
"learning_rate": 1.2930780045908777e-06,
|
| 975 |
+
"loss": 0.5104885101318359,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.7700831024930748,
|
| 980 |
+
"grad_norm": 0.5107504874213492,
|
| 981 |
+
"learning_rate": 4.028793452574461e-07,
|
| 982 |
+
"loss": 0.5073337554931641,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.7750692520775623,
|
| 987 |
+
"step": 1399,
|
| 988 |
+
"total_flos": 9636328589230080.0,
|
| 989 |
+
"train_loss": 0.046684147887267415,
|
| 990 |
+
"train_runtime": 5206.8179,
|
| 991 |
+
"train_samples_per_second": 25.794,
|
| 992 |
+
"train_steps_per_second": 0.269
|
| 993 |
+
}
|
| 994 |
+
],
|
| 995 |
+
"logging_steps": 10,
|
| 996 |
+
"max_steps": 1399,
|
| 997 |
+
"num_input_tokens_seen": 0,
|
| 998 |
+
"num_train_epochs": 1,
|
| 999 |
+
"save_steps": 1000000,
|
| 1000 |
+
"stateful_callbacks": {
|
| 1001 |
+
"TrainerControl": {
|
| 1002 |
+
"args": {
|
| 1003 |
+
"should_epoch_stop": false,
|
| 1004 |
+
"should_evaluate": false,
|
| 1005 |
+
"should_log": false,
|
| 1006 |
+
"should_save": true,
|
| 1007 |
+
"should_training_stop": true
|
| 1008 |
+
},
|
| 1009 |
+
"attributes": {}
|
| 1010 |
+
}
|
| 1011 |
+
},
|
| 1012 |
+
"total_flos": 9636328589230080.0,
|
| 1013 |
+
"train_batch_size": 1,
|
| 1014 |
+
"trial_name": null,
|
| 1015 |
+
"trial_params": null
|
| 1016 |
+
}
|
g2_6_oldcode_review_newcode_v4__edit/1000M/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8593dd702d50c692df34518010a8272c7213b77686be01d56db6c7d2f86945c
|
| 3 |
+
size 8273
|
g2_6_oldcode_review_newcode_v4__edit/1000M/training_loss.png
ADDED
|