Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- 200M/chat_template.jinja +1 -0
- 200M/config.json +170 -0
- 200M/generation_config.json +17 -0
- 200M/latest +1 -0
- 200M/model.safetensors +3 -0
- 200M/processor_config.json +62 -0
- 200M/rng_state_0.pth +3 -0
- 200M/rng_state_1.pth +3 -0
- 200M/rng_state_10.pth +3 -0
- 200M/rng_state_11.pth +3 -0
- 200M/rng_state_2.pth +3 -0
- 200M/rng_state_3.pth +3 -0
- 200M/rng_state_4.pth +3 -0
- 200M/rng_state_5.pth +3 -0
- 200M/rng_state_6.pth +3 -0
- 200M/rng_state_7.pth +3 -0
- 200M/rng_state_8.pth +3 -0
- 200M/rng_state_9.pth +3 -0
- 200M/scheduler.pt +3 -0
- 200M/tokenizer.json +3 -0
- 200M/tokenizer_config.json +56 -0
- 200M/trainer_state.json +1455 -0
- 200M/training_args.bin +3 -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 |
+
200M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
200M/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 }}{% endif %}{% endfor %}
|
200M/config.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4UnifiedForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"_name_or_path": "",
|
| 7 |
+
"architectures": null,
|
| 8 |
+
"audio_embed_dim": 640,
|
| 9 |
+
"chunk_size_feed_forward": 0,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"is_encoder_decoder": false,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0,
|
| 19 |
+
"LABEL_1": 1
|
| 20 |
+
},
|
| 21 |
+
"model_type": "gemma4_unified_audio",
|
| 22 |
+
"output_attentions": false,
|
| 23 |
+
"output_hidden_states": false,
|
| 24 |
+
"problem_type": null,
|
| 25 |
+
"return_dict": true,
|
| 26 |
+
"rms_norm_eps": 1e-06
|
| 27 |
+
},
|
| 28 |
+
"audio_token_id": 258881,
|
| 29 |
+
"boa_token_id": 256000,
|
| 30 |
+
"boi_token_id": 255999,
|
| 31 |
+
"bos_token_id": 2,
|
| 32 |
+
"dtype": "bfloat16",
|
| 33 |
+
"eoa_token_index": 258883,
|
| 34 |
+
"eoi_token_id": 258882,
|
| 35 |
+
"eos_token_id": 1,
|
| 36 |
+
"hidden_size": 3840,
|
| 37 |
+
"image_token_id": 258880,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"model_type": "gemma4_unified",
|
| 40 |
+
"pad_token_id": 0,
|
| 41 |
+
"text_config": {
|
| 42 |
+
"attention_bias": false,
|
| 43 |
+
"attention_dropout": 0.0,
|
| 44 |
+
"attention_k_eq_v": true,
|
| 45 |
+
"bos_token_id": 2,
|
| 46 |
+
"dtype": "bfloat16",
|
| 47 |
+
"enable_moe_block": false,
|
| 48 |
+
"eos_token_id": 1,
|
| 49 |
+
"final_logit_softcapping": 30.0,
|
| 50 |
+
"global_head_dim": 512,
|
| 51 |
+
"head_dim": 256,
|
| 52 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 53 |
+
"hidden_size": 3840,
|
| 54 |
+
"hidden_size_per_layer_input": 0,
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 15360,
|
| 57 |
+
"layer_types": [
|
| 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 |
+
"sliding_attention",
|
| 77 |
+
"sliding_attention",
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"sliding_attention",
|
| 80 |
+
"sliding_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"sliding_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"sliding_attention",
|
| 86 |
+
"sliding_attention",
|
| 87 |
+
"full_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"sliding_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"sliding_attention",
|
| 92 |
+
"sliding_attention",
|
| 93 |
+
"full_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"sliding_attention",
|
| 96 |
+
"sliding_attention",
|
| 97 |
+
"sliding_attention",
|
| 98 |
+
"sliding_attention",
|
| 99 |
+
"full_attention",
|
| 100 |
+
"sliding_attention",
|
| 101 |
+
"sliding_attention",
|
| 102 |
+
"sliding_attention",
|
| 103 |
+
"sliding_attention",
|
| 104 |
+
"sliding_attention",
|
| 105 |
+
"full_attention"
|
| 106 |
+
],
|
| 107 |
+
"max_position_embeddings": 262144,
|
| 108 |
+
"model_type": "gemma4_unified_text",
|
| 109 |
+
"moe_intermediate_size": null,
|
| 110 |
+
"num_attention_heads": 16,
|
| 111 |
+
"num_experts": null,
|
| 112 |
+
"num_global_key_value_heads": 1,
|
| 113 |
+
"num_hidden_layers": 48,
|
| 114 |
+
"num_key_value_heads": 8,
|
| 115 |
+
"num_kv_shared_layers": 0,
|
| 116 |
+
"pad_token_id": 0,
|
| 117 |
+
"rms_norm_eps": 1e-06,
|
| 118 |
+
"rope_parameters": {
|
| 119 |
+
"full_attention": {
|
| 120 |
+
"partial_rotary_factor": 0.25,
|
| 121 |
+
"rope_theta": 1000000.0,
|
| 122 |
+
"rope_type": "proportional"
|
| 123 |
+
},
|
| 124 |
+
"sliding_attention": {
|
| 125 |
+
"rope_theta": 10000.0,
|
| 126 |
+
"rope_type": "default"
|
| 127 |
+
}
|
| 128 |
+
},
|
| 129 |
+
"sliding_window": 1024,
|
| 130 |
+
"tie_word_embeddings": true,
|
| 131 |
+
"top_k_experts": null,
|
| 132 |
+
"use_bidirectional_attention": "vision",
|
| 133 |
+
"use_cache": false,
|
| 134 |
+
"use_double_wide_mlp": false,
|
| 135 |
+
"vocab_size": 262144,
|
| 136 |
+
"vocab_size_per_layer_input": 262144
|
| 137 |
+
},
|
| 138 |
+
"tie_word_embeddings": true,
|
| 139 |
+
"transformers_version": "5.10.0",
|
| 140 |
+
"use_cache": false,
|
| 141 |
+
"video_token_id": 258884,
|
| 142 |
+
"vision_config": {
|
| 143 |
+
"_name_or_path": "",
|
| 144 |
+
"architectures": null,
|
| 145 |
+
"chunk_size_feed_forward": 0,
|
| 146 |
+
"dtype": "bfloat16",
|
| 147 |
+
"id2label": {
|
| 148 |
+
"0": "LABEL_0",
|
| 149 |
+
"1": "LABEL_1"
|
| 150 |
+
},
|
| 151 |
+
"initializer_range": 0.02,
|
| 152 |
+
"is_encoder_decoder": false,
|
| 153 |
+
"label2id": {
|
| 154 |
+
"LABEL_0": 0,
|
| 155 |
+
"LABEL_1": 1
|
| 156 |
+
},
|
| 157 |
+
"mm_embed_dim": 3840,
|
| 158 |
+
"mm_posemb_size": 1120,
|
| 159 |
+
"model_type": "gemma4_unified_vision",
|
| 160 |
+
"num_soft_tokens": 280,
|
| 161 |
+
"output_attentions": false,
|
| 162 |
+
"output_hidden_states": false,
|
| 163 |
+
"output_proj_dims": 3840,
|
| 164 |
+
"patch_size": 16,
|
| 165 |
+
"pooling_kernel_size": 3,
|
| 166 |
+
"problem_type": null,
|
| 167 |
+
"return_dict": true,
|
| 168 |
+
"rms_norm_eps": 1e-06
|
| 169 |
+
}
|
| 170 |
+
}
|
200M/generation_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"suppress_tokens": [
|
| 10 |
+
258883,
|
| 11 |
+
258882
|
| 12 |
+
],
|
| 13 |
+
"temperature": 1.0,
|
| 14 |
+
"top_k": 64,
|
| 15 |
+
"top_p": 0.95,
|
| 16 |
+
"transformers_version": "5.10.0"
|
| 17 |
+
}
|
200M/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step2035
|
200M/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bdbefb927428c2c7e44ae174e8ba5ab1757e6e2fd97e58724f4e3f493a364c7
|
| 3 |
+
size 23919549408
|
200M/processor_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"audio_samples_per_token": 640,
|
| 6 |
+
"feature_extractor_type": "Gemma4UnifiedAudioFeatureExtractor",
|
| 7 |
+
"feature_size": 640,
|
| 8 |
+
"padding_side": "right",
|
| 9 |
+
"padding_value": 0.0,
|
| 10 |
+
"return_attention_mask": true,
|
| 11 |
+
"sampling_rate": 16000
|
| 12 |
+
},
|
| 13 |
+
"image_processor": {
|
| 14 |
+
"do_convert_rgb": true,
|
| 15 |
+
"do_normalize": false,
|
| 16 |
+
"do_rescale": true,
|
| 17 |
+
"do_resize": true,
|
| 18 |
+
"image_mean": [
|
| 19 |
+
0.0,
|
| 20 |
+
0.0,
|
| 21 |
+
0.0
|
| 22 |
+
],
|
| 23 |
+
"image_processor_type": "Gemma4UnifiedImageProcessor",
|
| 24 |
+
"image_std": [
|
| 25 |
+
1.0,
|
| 26 |
+
1.0,
|
| 27 |
+
1.0
|
| 28 |
+
],
|
| 29 |
+
"max_soft_tokens": 280,
|
| 30 |
+
"patch_size": 16,
|
| 31 |
+
"pooling_kernel_size": 3,
|
| 32 |
+
"resample": 3,
|
| 33 |
+
"rescale_factor": 0.00392156862745098
|
| 34 |
+
},
|
| 35 |
+
"image_seq_length": 280,
|
| 36 |
+
"processor_class": "Gemma4UnifiedProcessor",
|
| 37 |
+
"video_processor": {
|
| 38 |
+
"do_convert_rgb": true,
|
| 39 |
+
"do_normalize": true,
|
| 40 |
+
"do_rescale": true,
|
| 41 |
+
"do_resize": true,
|
| 42 |
+
"do_sample_frames": true,
|
| 43 |
+
"image_mean": [
|
| 44 |
+
0.0,
|
| 45 |
+
0.0,
|
| 46 |
+
0.0
|
| 47 |
+
],
|
| 48 |
+
"image_std": [
|
| 49 |
+
1.0,
|
| 50 |
+
1.0,
|
| 51 |
+
1.0
|
| 52 |
+
],
|
| 53 |
+
"max_soft_tokens": 70,
|
| 54 |
+
"num_frames": 32,
|
| 55 |
+
"patch_size": 16,
|
| 56 |
+
"pooling_kernel_size": 3,
|
| 57 |
+
"resample": 3,
|
| 58 |
+
"rescale_factor": 0.00392156862745098,
|
| 59 |
+
"return_metadata": false,
|
| 60 |
+
"video_processor_type": "Gemma4UnifiedVideoProcessor"
|
| 61 |
+
}
|
| 62 |
+
}
|
200M/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7dcf54a8dbd1fff243640ddc034149fbe7c90ed70b8a95a6bb093e989a7577
|
| 3 |
+
size 14469
|
200M/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a2b0b9d330140afd742a57df45106276d425d38a78e53b0fd43dba9559f8d4
|
| 3 |
+
size 14469
|
200M/rng_state_10.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ce222f8f11fd62fd6cb82264500aefbc9e7ef16907ed3e4aa3a8a99c21d95d3
|
| 3 |
+
size 14476
|
200M/rng_state_11.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d07144bfc4ed675dda70ab66923d17d6f9233560b2db09689cbe1f262c590c88
|
| 3 |
+
size 14476
|
200M/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5db634f6ed5151d3c898fbe3c365f950516c404bed926de16b253b26e63c7cf
|
| 3 |
+
size 14469
|
200M/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad774eade44525098fff2d5910e3d16565fca4c2af29ed0bc4d9315a8ac9607a
|
| 3 |
+
size 14469
|
200M/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebdee1b37be2238764bcfeed9dad268e938248152b0fba60eaf89adda99eac0f
|
| 3 |
+
size 14469
|
200M/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6046157bd3d69a7cf6ee508b7359b30cb71488a11b11b07a614041b06813c553
|
| 3 |
+
size 14469
|
200M/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebc9300f101a324d0361f01aec1d57e26b57a703b4e536f4fe982c8ba57a9144
|
| 3 |
+
size 14469
|
200M/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:357df7b609d6ffd7f22b998281f7856a711ee83505e5ed2835959554b0185df7
|
| 3 |
+
size 14469
|
200M/rng_state_8.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb33667d752a94ade6841f62b8b8fcc22256b4712bd568b141bc690d4a42e11
|
| 3 |
+
size 14469
|
200M/rng_state_9.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:354a7a38e97ba11b8ad29bf4d00d74f92295b32124cff0ef46baa862aa9b0f2f
|
| 3 |
+
size 14469
|
200M/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea084231345496123a1e2e3e6e6377891838cfabbf1b42517ab7575e5966916e
|
| 3 |
+
size 1465
|
200M/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
|
| 3 |
+
size 32170070
|
200M/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": "Gemma4UnifiedProcessor",
|
| 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 |
+
}
|
200M/trainer_state.json
ADDED
|
@@ -0,0 +1,1455 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.07864734299516908,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2035,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0003864734299516908,
|
| 14 |
+
"grad_norm": 67.77150678538916,
|
| 15 |
+
"learning_rate": 2.910112359550562e-06,
|
| 16 |
+
"loss": 1.7119647979736328,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0007729468599033816,
|
| 21 |
+
"grad_norm": 112.20087349554393,
|
| 22 |
+
"learning_rate": 3.921348314606742e-06,
|
| 23 |
+
"loss": 1.0294610977172851,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0011594202898550724,
|
| 28 |
+
"grad_norm": 17.998285122767445,
|
| 29 |
+
"learning_rate": 4.932584269662922e-06,
|
| 30 |
+
"loss": 0.9339380264282227,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0015458937198067632,
|
| 35 |
+
"grad_norm": 44.13244966887987,
|
| 36 |
+
"learning_rate": 5.943820224719102e-06,
|
| 37 |
+
"loss": 0.8280322074890136,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.001932367149758454,
|
| 42 |
+
"grad_norm": 35.342167635210814,
|
| 43 |
+
"learning_rate": 6.955056179775282e-06,
|
| 44 |
+
"loss": 0.8310356140136719,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.002318840579710145,
|
| 49 |
+
"grad_norm": 13.961543042810325,
|
| 50 |
+
"learning_rate": 7.966292134831462e-06,
|
| 51 |
+
"loss": 0.8424642562866211,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.002705314009661836,
|
| 56 |
+
"grad_norm": 16.09056628824688,
|
| 57 |
+
"learning_rate": 8.977528089887641e-06,
|
| 58 |
+
"loss": 0.8591781616210937,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0030917874396135265,
|
| 63 |
+
"grad_norm": 54.47103241018983,
|
| 64 |
+
"learning_rate": 9.988764044943822e-06,
|
| 65 |
+
"loss": 0.8048875808715821,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0034782608695652175,
|
| 70 |
+
"grad_norm": 288.41808740691243,
|
| 71 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 72 |
+
"loss": 0.7839107513427734,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.003864734299516908,
|
| 77 |
+
"grad_norm": 90.30364936720191,
|
| 78 |
+
"learning_rate": 1.2011235955056182e-05,
|
| 79 |
+
"loss": 0.8227674484252929,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.004251207729468599,
|
| 84 |
+
"grad_norm": 7.031443917093176,
|
| 85 |
+
"learning_rate": 1.3022471910112362e-05,
|
| 86 |
+
"loss": 0.8219305038452148,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.00463768115942029,
|
| 91 |
+
"grad_norm": 64.81590934958837,
|
| 92 |
+
"learning_rate": 1.403370786516854e-05,
|
| 93 |
+
"loss": 0.8873563766479492,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00502415458937198,
|
| 98 |
+
"grad_norm": 7.4010759674397075,
|
| 99 |
+
"learning_rate": 1.504494382022472e-05,
|
| 100 |
+
"loss": 0.8595630645751953,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.005410628019323672,
|
| 105 |
+
"grad_norm": 19.21019328586394,
|
| 106 |
+
"learning_rate": 1.60561797752809e-05,
|
| 107 |
+
"loss": 0.8214578628540039,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.005797101449275362,
|
| 112 |
+
"grad_norm": 12.640756734713527,
|
| 113 |
+
"learning_rate": 1.706741573033708e-05,
|
| 114 |
+
"loss": 0.8313806533813477,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.006183574879227053,
|
| 119 |
+
"grad_norm": 30.722029453858426,
|
| 120 |
+
"learning_rate": 1.8078651685393256e-05,
|
| 121 |
+
"loss": 0.8253059387207031,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.006570048309178744,
|
| 126 |
+
"grad_norm": 9.610182761607462,
|
| 127 |
+
"learning_rate": 1.908988764044944e-05,
|
| 128 |
+
"loss": 0.8571659088134765,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.006956521739130435,
|
| 133 |
+
"grad_norm": 66.94480959155315,
|
| 134 |
+
"learning_rate": 2e-05,
|
| 135 |
+
"loss": 0.825499439239502,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.007342995169082126,
|
| 140 |
+
"grad_norm": 18.927988413767896,
|
| 141 |
+
"learning_rate": 2e-05,
|
| 142 |
+
"loss": 0.8307562828063965,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.007729468599033816,
|
| 147 |
+
"grad_norm": 12.259205440850302,
|
| 148 |
+
"learning_rate": 2e-05,
|
| 149 |
+
"loss": 0.8559392929077149,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.008115942028985508,
|
| 154 |
+
"grad_norm": 4.705925662053298,
|
| 155 |
+
"learning_rate": 2e-05,
|
| 156 |
+
"loss": 0.8608473777770996,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.008502415458937198,
|
| 161 |
+
"grad_norm": 2.301827055644639,
|
| 162 |
+
"learning_rate": 2e-05,
|
| 163 |
+
"loss": 0.8078425407409668,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.008888888888888889,
|
| 168 |
+
"grad_norm": 7.309011200551571,
|
| 169 |
+
"learning_rate": 2e-05,
|
| 170 |
+
"loss": 0.8398617744445801,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.00927536231884058,
|
| 175 |
+
"grad_norm": 6.173820350919054,
|
| 176 |
+
"learning_rate": 2e-05,
|
| 177 |
+
"loss": 0.8554814338684082,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.00966183574879227,
|
| 182 |
+
"grad_norm": 6.755722543096072,
|
| 183 |
+
"learning_rate": 2e-05,
|
| 184 |
+
"loss": 0.8236814498901367,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.01004830917874396,
|
| 189 |
+
"grad_norm": 8.495921320038692,
|
| 190 |
+
"learning_rate": 2e-05,
|
| 191 |
+
"loss": 0.8807731628417969,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.010434782608695653,
|
| 196 |
+
"grad_norm": 6.836865467270201,
|
| 197 |
+
"learning_rate": 2e-05,
|
| 198 |
+
"loss": 0.8989522933959961,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.010821256038647344,
|
| 203 |
+
"grad_norm": 14.122874054097522,
|
| 204 |
+
"learning_rate": 2e-05,
|
| 205 |
+
"loss": 0.8458233833312988,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.011207729468599034,
|
| 210 |
+
"grad_norm": 16.985124793104738,
|
| 211 |
+
"learning_rate": 2e-05,
|
| 212 |
+
"loss": 0.8226848602294922,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.011594202898550725,
|
| 217 |
+
"grad_norm": 41.65329788058193,
|
| 218 |
+
"learning_rate": 2e-05,
|
| 219 |
+
"loss": 0.8596689224243164,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.011980676328502415,
|
| 224 |
+
"grad_norm": 4.572131278336222,
|
| 225 |
+
"learning_rate": 2e-05,
|
| 226 |
+
"loss": 0.8586993217468262,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.012367149758454106,
|
| 231 |
+
"grad_norm": 15.52553197362288,
|
| 232 |
+
"learning_rate": 2e-05,
|
| 233 |
+
"loss": 0.8715810775756836,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.012753623188405797,
|
| 238 |
+
"grad_norm": 2.099292672310561,
|
| 239 |
+
"learning_rate": 2e-05,
|
| 240 |
+
"loss": 0.859681510925293,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.013140096618357487,
|
| 245 |
+
"grad_norm": 2.9884282294816904,
|
| 246 |
+
"learning_rate": 2e-05,
|
| 247 |
+
"loss": 0.8609855651855469,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.01352657004830918,
|
| 252 |
+
"grad_norm": 2.13249355879509,
|
| 253 |
+
"learning_rate": 2e-05,
|
| 254 |
+
"loss": 0.8378034591674804,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.01391304347826087,
|
| 259 |
+
"grad_norm": 1.6770141008927584,
|
| 260 |
+
"learning_rate": 2e-05,
|
| 261 |
+
"loss": 0.8262413024902344,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.01429951690821256,
|
| 266 |
+
"grad_norm": 4.682041458440538,
|
| 267 |
+
"learning_rate": 2e-05,
|
| 268 |
+
"loss": 0.8071828842163086,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.014685990338164251,
|
| 273 |
+
"grad_norm": 1.8513588195141903,
|
| 274 |
+
"learning_rate": 2e-05,
|
| 275 |
+
"loss": 0.7924742698669434,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.015072463768115942,
|
| 280 |
+
"grad_norm": 2.4641373360496774,
|
| 281 |
+
"learning_rate": 2e-05,
|
| 282 |
+
"loss": 0.8004615783691407,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.015458937198067632,
|
| 287 |
+
"grad_norm": 2.3004772602625914,
|
| 288 |
+
"learning_rate": 2e-05,
|
| 289 |
+
"loss": 0.7985801219940185,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.015845410628019325,
|
| 294 |
+
"grad_norm": 2.0543279811562636,
|
| 295 |
+
"learning_rate": 2e-05,
|
| 296 |
+
"loss": 0.8145970344543457,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.016231884057971015,
|
| 301 |
+
"grad_norm": 11.830783545012162,
|
| 302 |
+
"learning_rate": 2e-05,
|
| 303 |
+
"loss": 0.8268651962280273,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.016618357487922706,
|
| 308 |
+
"grad_norm": 23.315575489389328,
|
| 309 |
+
"learning_rate": 2e-05,
|
| 310 |
+
"loss": 0.8241431236267089,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.017004830917874397,
|
| 315 |
+
"grad_norm": 21.42157001872646,
|
| 316 |
+
"learning_rate": 2e-05,
|
| 317 |
+
"loss": 0.8197898864746094,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.017391304347826087,
|
| 322 |
+
"grad_norm": 6.089448482941218,
|
| 323 |
+
"learning_rate": 2e-05,
|
| 324 |
+
"loss": 0.799440574645996,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.017777777777777778,
|
| 329 |
+
"grad_norm": 2.0297328988872207,
|
| 330 |
+
"learning_rate": 2e-05,
|
| 331 |
+
"loss": 0.7915650844573975,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.01816425120772947,
|
| 336 |
+
"grad_norm": 2.5804977642175406,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 0.8292923927307129,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.01855072463768116,
|
| 343 |
+
"grad_norm": 2.038221241470096,
|
| 344 |
+
"learning_rate": 2e-05,
|
| 345 |
+
"loss": 0.8466601371765137,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.01893719806763285,
|
| 350 |
+
"grad_norm": 2.6279678065101404,
|
| 351 |
+
"learning_rate": 2e-05,
|
| 352 |
+
"loss": 0.7829755306243896,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.01932367149758454,
|
| 357 |
+
"grad_norm": 3.6287666464295207,
|
| 358 |
+
"learning_rate": 2e-05,
|
| 359 |
+
"loss": 0.8295025825500488,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.01971014492753623,
|
| 364 |
+
"grad_norm": 5.056996216526932,
|
| 365 |
+
"learning_rate": 2e-05,
|
| 366 |
+
"loss": 0.8213679313659668,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.02009661835748792,
|
| 371 |
+
"grad_norm": 3.2319172805464556,
|
| 372 |
+
"learning_rate": 2e-05,
|
| 373 |
+
"loss": 0.8206055641174317,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.020483091787439612,
|
| 378 |
+
"grad_norm": 8.57107033721087,
|
| 379 |
+
"learning_rate": 2e-05,
|
| 380 |
+
"loss": 0.8187108039855957,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.020869565217391306,
|
| 385 |
+
"grad_norm": 2.3249597398057866,
|
| 386 |
+
"learning_rate": 2e-05,
|
| 387 |
+
"loss": 0.8607352256774903,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.021256038647342997,
|
| 392 |
+
"grad_norm": 4.207073762673164,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.803462028503418,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.021642512077294687,
|
| 399 |
+
"grad_norm": 2.16004233284329,
|
| 400 |
+
"learning_rate": 2e-05,
|
| 401 |
+
"loss": 0.8118793487548828,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.022028985507246378,
|
| 406 |
+
"grad_norm": 5.922676764922052,
|
| 407 |
+
"learning_rate": 2e-05,
|
| 408 |
+
"loss": 0.8660179138183594,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.02241545893719807,
|
| 413 |
+
"grad_norm": 2.8910298488294783,
|
| 414 |
+
"learning_rate": 2e-05,
|
| 415 |
+
"loss": 0.8383306503295899,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.02280193236714976,
|
| 420 |
+
"grad_norm": 10.435855529697001,
|
| 421 |
+
"learning_rate": 2e-05,
|
| 422 |
+
"loss": 0.8274753570556641,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.02318840579710145,
|
| 427 |
+
"grad_norm": 5.716952677601055,
|
| 428 |
+
"learning_rate": 2e-05,
|
| 429 |
+
"loss": 0.8341848373413085,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.02357487922705314,
|
| 434 |
+
"grad_norm": 1.7990410820641871,
|
| 435 |
+
"learning_rate": 2e-05,
|
| 436 |
+
"loss": 0.8170646667480469,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.02396135265700483,
|
| 441 |
+
"grad_norm": 2.5141846970054984,
|
| 442 |
+
"learning_rate": 2e-05,
|
| 443 |
+
"loss": 0.8089756965637207,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.02434782608695652,
|
| 448 |
+
"grad_norm": 1.644941789727098,
|
| 449 |
+
"learning_rate": 2e-05,
|
| 450 |
+
"loss": 0.7915188789367675,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.024734299516908212,
|
| 455 |
+
"grad_norm": 4.69436608310746,
|
| 456 |
+
"learning_rate": 2e-05,
|
| 457 |
+
"loss": 0.8204584121704102,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.025120772946859903,
|
| 462 |
+
"grad_norm": 14.985321654813715,
|
| 463 |
+
"learning_rate": 2e-05,
|
| 464 |
+
"loss": 0.8408443450927734,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.025507246376811593,
|
| 469 |
+
"grad_norm": 3.606103990135419,
|
| 470 |
+
"learning_rate": 2e-05,
|
| 471 |
+
"loss": 0.8335097312927247,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.025893719806763284,
|
| 476 |
+
"grad_norm": 302.2907667494139,
|
| 477 |
+
"learning_rate": 2e-05,
|
| 478 |
+
"loss": 0.8303115844726563,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.026280193236714974,
|
| 483 |
+
"grad_norm": 5.094641064796761,
|
| 484 |
+
"learning_rate": 2e-05,
|
| 485 |
+
"loss": 0.8183450698852539,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.02666666666666667,
|
| 490 |
+
"grad_norm": 7.71531360876406,
|
| 491 |
+
"learning_rate": 2e-05,
|
| 492 |
+
"loss": 0.8168371200561524,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.02705314009661836,
|
| 497 |
+
"grad_norm": 27.557957472594705,
|
| 498 |
+
"learning_rate": 2e-05,
|
| 499 |
+
"loss": 0.8344195365905762,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.02743961352657005,
|
| 504 |
+
"grad_norm": 6.340736949473045,
|
| 505 |
+
"learning_rate": 2e-05,
|
| 506 |
+
"loss": 0.8478621482849121,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.02782608695652174,
|
| 511 |
+
"grad_norm": 84.49603950900422,
|
| 512 |
+
"learning_rate": 2e-05,
|
| 513 |
+
"loss": 0.8494409561157227,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.02821256038647343,
|
| 518 |
+
"grad_norm": 5.239994048119582,
|
| 519 |
+
"learning_rate": 2e-05,
|
| 520 |
+
"loss": 0.8430055618286133,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.02859903381642512,
|
| 525 |
+
"grad_norm": 6.81571454851921,
|
| 526 |
+
"learning_rate": 2e-05,
|
| 527 |
+
"loss": 0.8379552841186524,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.028985507246376812,
|
| 532 |
+
"grad_norm": 13.230544669517375,
|
| 533 |
+
"learning_rate": 2e-05,
|
| 534 |
+
"loss": 0.8137977600097657,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.029371980676328503,
|
| 539 |
+
"grad_norm": 10.83917272801397,
|
| 540 |
+
"learning_rate": 2e-05,
|
| 541 |
+
"loss": 0.8010368347167969,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.029758454106280193,
|
| 546 |
+
"grad_norm": 4.561007311907072,
|
| 547 |
+
"learning_rate": 2e-05,
|
| 548 |
+
"loss": 0.8132765769958497,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.030144927536231884,
|
| 553 |
+
"grad_norm": 5.052478275742948,
|
| 554 |
+
"learning_rate": 2e-05,
|
| 555 |
+
"loss": 0.8024440765380859,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.030531400966183574,
|
| 560 |
+
"grad_norm": 39.20779782791551,
|
| 561 |
+
"learning_rate": 2e-05,
|
| 562 |
+
"loss": 0.8082746505737305,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.030917874396135265,
|
| 567 |
+
"grad_norm": 6.722990812199062,
|
| 568 |
+
"learning_rate": 2e-05,
|
| 569 |
+
"loss": 0.7964837551116943,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.03130434782608696,
|
| 574 |
+
"grad_norm": 6.263608751717215,
|
| 575 |
+
"learning_rate": 2e-05,
|
| 576 |
+
"loss": 0.8117972373962402,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.03169082125603865,
|
| 581 |
+
"grad_norm": 6.362861042949148,
|
| 582 |
+
"learning_rate": 2e-05,
|
| 583 |
+
"loss": 0.8188319206237793,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.03207729468599034,
|
| 588 |
+
"grad_norm": 6.379235603582932,
|
| 589 |
+
"learning_rate": 2e-05,
|
| 590 |
+
"loss": 0.7999361991882324,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.03246376811594203,
|
| 595 |
+
"grad_norm": 7.771520162515829,
|
| 596 |
+
"learning_rate": 2e-05,
|
| 597 |
+
"loss": 0.8278095245361328,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.03285024154589372,
|
| 602 |
+
"grad_norm": 3.6283672901509307,
|
| 603 |
+
"learning_rate": 2e-05,
|
| 604 |
+
"loss": 0.8165772438049317,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.03323671497584541,
|
| 609 |
+
"grad_norm": 24.13531059310475,
|
| 610 |
+
"learning_rate": 2e-05,
|
| 611 |
+
"loss": 0.8282254219055176,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.0336231884057971,
|
| 616 |
+
"grad_norm": 6.38211185754252,
|
| 617 |
+
"learning_rate": 2e-05,
|
| 618 |
+
"loss": 0.857562255859375,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.03400966183574879,
|
| 623 |
+
"grad_norm": 8.151353292941916,
|
| 624 |
+
"learning_rate": 2e-05,
|
| 625 |
+
"loss": 0.8778319358825684,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.034396135265700484,
|
| 630 |
+
"grad_norm": 2.6425732312042793,
|
| 631 |
+
"learning_rate": 2e-05,
|
| 632 |
+
"loss": 0.8224431991577148,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.034782608695652174,
|
| 637 |
+
"grad_norm": 3.5769751025573835,
|
| 638 |
+
"learning_rate": 2e-05,
|
| 639 |
+
"loss": 0.8090167999267578,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.035169082125603865,
|
| 644 |
+
"grad_norm": 4.710064964796984,
|
| 645 |
+
"learning_rate": 2e-05,
|
| 646 |
+
"loss": 0.7755887508392334,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.035555555555555556,
|
| 651 |
+
"grad_norm": 2.85171049842582,
|
| 652 |
+
"learning_rate": 2e-05,
|
| 653 |
+
"loss": 0.80325927734375,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.035942028985507246,
|
| 658 |
+
"grad_norm": 2.7025040213443625,
|
| 659 |
+
"learning_rate": 2e-05,
|
| 660 |
+
"loss": 0.8224540710449219,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.03632850241545894,
|
| 665 |
+
"grad_norm": 4.365935909605305,
|
| 666 |
+
"learning_rate": 2e-05,
|
| 667 |
+
"loss": 0.8001300811767578,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.03671497584541063,
|
| 672 |
+
"grad_norm": 4.205991130813683,
|
| 673 |
+
"learning_rate": 2e-05,
|
| 674 |
+
"loss": 0.8388648986816406,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.03710144927536232,
|
| 679 |
+
"grad_norm": 9.511180584595577,
|
| 680 |
+
"learning_rate": 2e-05,
|
| 681 |
+
"loss": 0.8006820678710938,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.03748792270531401,
|
| 686 |
+
"grad_norm": 1.8991371909927346,
|
| 687 |
+
"learning_rate": 2e-05,
|
| 688 |
+
"loss": 0.7927989959716797,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.0378743961352657,
|
| 693 |
+
"grad_norm": 1.7204963535857005,
|
| 694 |
+
"learning_rate": 2e-05,
|
| 695 |
+
"loss": 0.7866291046142578,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.03826086956521739,
|
| 700 |
+
"grad_norm": 4.982975467165141,
|
| 701 |
+
"learning_rate": 2e-05,
|
| 702 |
+
"loss": 0.8541565895080566,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.03864734299516908,
|
| 707 |
+
"grad_norm": 1.4823804814569383,
|
| 708 |
+
"learning_rate": 2e-05,
|
| 709 |
+
"loss": 0.7768624782562256,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.03903381642512077,
|
| 714 |
+
"grad_norm": 1.6741186213295625,
|
| 715 |
+
"learning_rate": 2e-05,
|
| 716 |
+
"loss": 0.7901049613952636,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.03942028985507246,
|
| 721 |
+
"grad_norm": 2.4322679920118455,
|
| 722 |
+
"learning_rate": 2e-05,
|
| 723 |
+
"loss": 0.7638983726501465,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.03980676328502415,
|
| 728 |
+
"grad_norm": 3.3701720746584383,
|
| 729 |
+
"learning_rate": 2e-05,
|
| 730 |
+
"loss": 0.7828890800476074,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.04019323671497584,
|
| 735 |
+
"grad_norm": 2.0742844849026607,
|
| 736 |
+
"learning_rate": 2e-05,
|
| 737 |
+
"loss": 0.8018475532531738,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.04057971014492753,
|
| 742 |
+
"grad_norm": 2.1569898099072904,
|
| 743 |
+
"learning_rate": 2e-05,
|
| 744 |
+
"loss": 0.7848191738128663,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.040966183574879224,
|
| 749 |
+
"grad_norm": 1.3882337646082599,
|
| 750 |
+
"learning_rate": 2e-05,
|
| 751 |
+
"loss": 0.7792089462280274,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.041352657004830914,
|
| 756 |
+
"grad_norm": 2.662094444417472,
|
| 757 |
+
"learning_rate": 2e-05,
|
| 758 |
+
"loss": 0.793889045715332,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.04173913043478261,
|
| 763 |
+
"grad_norm": 2.587246330505362,
|
| 764 |
+
"learning_rate": 2e-05,
|
| 765 |
+
"loss": 0.7864011287689209,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.0421256038647343,
|
| 770 |
+
"grad_norm": 1.0896303438627253,
|
| 771 |
+
"learning_rate": 2e-05,
|
| 772 |
+
"loss": 0.7887033462524414,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.04251207729468599,
|
| 777 |
+
"grad_norm": 1.6180241575772059,
|
| 778 |
+
"learning_rate": 2e-05,
|
| 779 |
+
"loss": 0.7555316925048828,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.042898550724637684,
|
| 784 |
+
"grad_norm": 5.15524054228135,
|
| 785 |
+
"learning_rate": 2e-05,
|
| 786 |
+
"loss": 0.7596688747406006,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.043285024154589374,
|
| 791 |
+
"grad_norm": 3.791811827235934,
|
| 792 |
+
"learning_rate": 2e-05,
|
| 793 |
+
"loss": 0.7762317180633544,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.043671497584541065,
|
| 798 |
+
"grad_norm": 3.8840676386572754,
|
| 799 |
+
"learning_rate": 2e-05,
|
| 800 |
+
"loss": 0.7993937492370605,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.044057971014492756,
|
| 805 |
+
"grad_norm": 1.7203756023551415,
|
| 806 |
+
"learning_rate": 2e-05,
|
| 807 |
+
"loss": 0.8044867515563965,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.044444444444444446,
|
| 812 |
+
"grad_norm": 1.8455815673442082,
|
| 813 |
+
"learning_rate": 2e-05,
|
| 814 |
+
"loss": 0.7740165710449218,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.04483091787439614,
|
| 819 |
+
"grad_norm": 1.2497425235654502,
|
| 820 |
+
"learning_rate": 2e-05,
|
| 821 |
+
"loss": 0.7792739868164062,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.04521739130434783,
|
| 826 |
+
"grad_norm": 3.582519109266027,
|
| 827 |
+
"learning_rate": 2e-05,
|
| 828 |
+
"loss": 0.7844886302947998,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.04560386473429952,
|
| 833 |
+
"grad_norm": 1.7447476237477404,
|
| 834 |
+
"learning_rate": 2e-05,
|
| 835 |
+
"loss": 0.7678474426269531,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.04599033816425121,
|
| 840 |
+
"grad_norm": 2.3052344816348285,
|
| 841 |
+
"learning_rate": 2e-05,
|
| 842 |
+
"loss": 0.7841787338256836,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.0463768115942029,
|
| 847 |
+
"grad_norm": 6.171873978979098,
|
| 848 |
+
"learning_rate": 2e-05,
|
| 849 |
+
"loss": 0.7667727470397949,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.04676328502415459,
|
| 854 |
+
"grad_norm": 2.5238752863132166,
|
| 855 |
+
"learning_rate": 2e-05,
|
| 856 |
+
"loss": 0.7614020824432373,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.04714975845410628,
|
| 861 |
+
"grad_norm": 3.3006024749410345,
|
| 862 |
+
"learning_rate": 2e-05,
|
| 863 |
+
"loss": 0.7787034988403321,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.04753623188405797,
|
| 868 |
+
"grad_norm": 1.7800834333389988,
|
| 869 |
+
"learning_rate": 2e-05,
|
| 870 |
+
"loss": 0.781245756149292,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.04792270531400966,
|
| 875 |
+
"grad_norm": 4.086703804045758,
|
| 876 |
+
"learning_rate": 2e-05,
|
| 877 |
+
"loss": 0.7704942226409912,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.04830917874396135,
|
| 882 |
+
"grad_norm": 1.8232412748458093,
|
| 883 |
+
"learning_rate": 2e-05,
|
| 884 |
+
"loss": 0.830727481842041,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.04869565217391304,
|
| 889 |
+
"grad_norm": 1.438606233505821,
|
| 890 |
+
"learning_rate": 2e-05,
|
| 891 |
+
"loss": 0.7969734191894531,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.04908212560386473,
|
| 896 |
+
"grad_norm": 14.874207481468607,
|
| 897 |
+
"learning_rate": 2e-05,
|
| 898 |
+
"loss": 0.7737374305725098,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.049468599033816424,
|
| 903 |
+
"grad_norm": 1.8577472378752176,
|
| 904 |
+
"learning_rate": 2e-05,
|
| 905 |
+
"loss": 0.7808979034423829,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.049855072463768114,
|
| 910 |
+
"grad_norm": 1.1647916231280007,
|
| 911 |
+
"learning_rate": 2e-05,
|
| 912 |
+
"loss": 0.7798149108886718,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.050241545893719805,
|
| 917 |
+
"grad_norm": 1.8949891297132515,
|
| 918 |
+
"learning_rate": 2e-05,
|
| 919 |
+
"loss": 0.7773360252380371,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.050628019323671496,
|
| 924 |
+
"grad_norm": 1.8051946173023403,
|
| 925 |
+
"learning_rate": 2e-05,
|
| 926 |
+
"loss": 0.7962361812591553,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.051014492753623186,
|
| 931 |
+
"grad_norm": 8.517857032168914,
|
| 932 |
+
"learning_rate": 2e-05,
|
| 933 |
+
"loss": 0.7579530715942383,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.05140096618357488,
|
| 938 |
+
"grad_norm": 1.2056710567353992,
|
| 939 |
+
"learning_rate": 2e-05,
|
| 940 |
+
"loss": 0.7956658840179444,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.05178743961352657,
|
| 945 |
+
"grad_norm": 1.5620096177153822,
|
| 946 |
+
"learning_rate": 2e-05,
|
| 947 |
+
"loss": 0.7909909248352051,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.05217391304347826,
|
| 952 |
+
"grad_norm": 1.2051599267987412,
|
| 953 |
+
"learning_rate": 2e-05,
|
| 954 |
+
"loss": 0.802952766418457,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.05256038647342995,
|
| 959 |
+
"grad_norm": 1.442909003316718,
|
| 960 |
+
"learning_rate": 2e-05,
|
| 961 |
+
"loss": 0.792842435836792,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.05294685990338164,
|
| 966 |
+
"grad_norm": 1.8033837673657727,
|
| 967 |
+
"learning_rate": 2e-05,
|
| 968 |
+
"loss": 0.8045886039733887,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.05333333333333334,
|
| 973 |
+
"grad_norm": 1.7301184849803795,
|
| 974 |
+
"learning_rate": 2e-05,
|
| 975 |
+
"loss": 0.7730770111083984,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.05371980676328503,
|
| 980 |
+
"grad_norm": 2.593314064685021,
|
| 981 |
+
"learning_rate": 2e-05,
|
| 982 |
+
"loss": 0.7898385524749756,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.05410628019323672,
|
| 987 |
+
"grad_norm": 2.6612126149781123,
|
| 988 |
+
"learning_rate": 2e-05,
|
| 989 |
+
"loss": 0.7972373008728028,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.05449275362318841,
|
| 994 |
+
"grad_norm": 4.014591492016486,
|
| 995 |
+
"learning_rate": 2e-05,
|
| 996 |
+
"loss": 0.7940009593963623,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.0548792270531401,
|
| 1001 |
+
"grad_norm": 1.88666817691601,
|
| 1002 |
+
"learning_rate": 2e-05,
|
| 1003 |
+
"loss": 0.7976803779602051,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.05526570048309179,
|
| 1008 |
+
"grad_norm": 1.6808638117085843,
|
| 1009 |
+
"learning_rate": 2e-05,
|
| 1010 |
+
"loss": 0.7751292228698731,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.05565217391304348,
|
| 1015 |
+
"grad_norm": 2.8607658596215573,
|
| 1016 |
+
"learning_rate": 2e-05,
|
| 1017 |
+
"loss": 0.7797608375549316,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.05603864734299517,
|
| 1022 |
+
"grad_norm": 1.743259772518007,
|
| 1023 |
+
"learning_rate": 2e-05,
|
| 1024 |
+
"loss": 0.7893115520477295,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.05642512077294686,
|
| 1029 |
+
"grad_norm": 4.094105063418816,
|
| 1030 |
+
"learning_rate": 2e-05,
|
| 1031 |
+
"loss": 0.7623452186584473,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.05681159420289855,
|
| 1036 |
+
"grad_norm": 1.0326374629324264,
|
| 1037 |
+
"learning_rate": 2e-05,
|
| 1038 |
+
"loss": 0.8003641128540039,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.05719806763285024,
|
| 1043 |
+
"grad_norm": 1.5470981584627885,
|
| 1044 |
+
"learning_rate": 2e-05,
|
| 1045 |
+
"loss": 0.7471415519714355,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.05758454106280193,
|
| 1050 |
+
"grad_norm": 4.233012132760419,
|
| 1051 |
+
"learning_rate": 2e-05,
|
| 1052 |
+
"loss": 0.8017045974731445,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.057971014492753624,
|
| 1057 |
+
"grad_norm": 1.5670919578440439,
|
| 1058 |
+
"learning_rate": 2e-05,
|
| 1059 |
+
"loss": 0.7809749603271484,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.058357487922705314,
|
| 1064 |
+
"grad_norm": 1.1146358925152047,
|
| 1065 |
+
"learning_rate": 2e-05,
|
| 1066 |
+
"loss": 0.8092234611511231,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.058743961352657005,
|
| 1071 |
+
"grad_norm": 1.8519058887339446,
|
| 1072 |
+
"learning_rate": 2e-05,
|
| 1073 |
+
"loss": 0.7762881755828858,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.059130434782608696,
|
| 1078 |
+
"grad_norm": 1.842244630499373,
|
| 1079 |
+
"learning_rate": 2e-05,
|
| 1080 |
+
"loss": 0.7717338085174561,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.059516908212560386,
|
| 1085 |
+
"grad_norm": 1.8659924669555197,
|
| 1086 |
+
"learning_rate": 2e-05,
|
| 1087 |
+
"loss": 0.8045551300048828,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.05990338164251208,
|
| 1092 |
+
"grad_norm": 1.789268515534286,
|
| 1093 |
+
"learning_rate": 2e-05,
|
| 1094 |
+
"loss": 0.802666187286377,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.06028985507246377,
|
| 1099 |
+
"grad_norm": 3.049390694136811,
|
| 1100 |
+
"learning_rate": 2e-05,
|
| 1101 |
+
"loss": 0.7977540493011475,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.06067632850241546,
|
| 1106 |
+
"grad_norm": 1.1550233137997092,
|
| 1107 |
+
"learning_rate": 2e-05,
|
| 1108 |
+
"loss": 0.759410810470581,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.06106280193236715,
|
| 1113 |
+
"grad_norm": 1.4840972042589198,
|
| 1114 |
+
"learning_rate": 2e-05,
|
| 1115 |
+
"loss": 0.7568341255187988,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.06144927536231884,
|
| 1120 |
+
"grad_norm": 2.4324918941876517,
|
| 1121 |
+
"learning_rate": 2e-05,
|
| 1122 |
+
"loss": 0.7721347808837891,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.06183574879227053,
|
| 1127 |
+
"grad_norm": 1.3236007075392429,
|
| 1128 |
+
"learning_rate": 2e-05,
|
| 1129 |
+
"loss": 0.7291332244873047,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.06222222222222222,
|
| 1134 |
+
"grad_norm": 1.8825475500130031,
|
| 1135 |
+
"learning_rate": 2e-05,
|
| 1136 |
+
"loss": 0.7765389919281006,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.06260869565217392,
|
| 1141 |
+
"grad_norm": 1.5021722283739194,
|
| 1142 |
+
"learning_rate": 2e-05,
|
| 1143 |
+
"loss": 0.7942019939422608,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.0629951690821256,
|
| 1148 |
+
"grad_norm": 1.3488892169893916,
|
| 1149 |
+
"learning_rate": 2e-05,
|
| 1150 |
+
"loss": 0.7698382377624512,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.0633816425120773,
|
| 1155 |
+
"grad_norm": 2.412898234110765,
|
| 1156 |
+
"learning_rate": 2e-05,
|
| 1157 |
+
"loss": 0.7915114402770996,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.06376811594202898,
|
| 1162 |
+
"grad_norm": 4.032177721449734,
|
| 1163 |
+
"learning_rate": 2e-05,
|
| 1164 |
+
"loss": 0.767926549911499,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.06415458937198068,
|
| 1169 |
+
"grad_norm": 3.3886389099102976,
|
| 1170 |
+
"learning_rate": 2e-05,
|
| 1171 |
+
"loss": 0.7934833526611328,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.06454106280193236,
|
| 1176 |
+
"grad_norm": 1.8196514648355098,
|
| 1177 |
+
"learning_rate": 2e-05,
|
| 1178 |
+
"loss": 0.8287544250488281,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.06492753623188406,
|
| 1183 |
+
"grad_norm": 1.933296233701157,
|
| 1184 |
+
"learning_rate": 2e-05,
|
| 1185 |
+
"loss": 0.7792496681213379,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.06531400966183575,
|
| 1190 |
+
"grad_norm": 5.5160092569417944,
|
| 1191 |
+
"learning_rate": 2e-05,
|
| 1192 |
+
"loss": 0.7874814987182617,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.06570048309178744,
|
| 1197 |
+
"grad_norm": 2.6740319109507054,
|
| 1198 |
+
"learning_rate": 2e-05,
|
| 1199 |
+
"loss": 0.7673942565917968,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.06608695652173913,
|
| 1204 |
+
"grad_norm": 4.46192092842804,
|
| 1205 |
+
"learning_rate": 2e-05,
|
| 1206 |
+
"loss": 0.7866016387939453,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.06647342995169082,
|
| 1211 |
+
"grad_norm": 9.393669028550853,
|
| 1212 |
+
"learning_rate": 2e-05,
|
| 1213 |
+
"loss": 0.7943299770355224,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.06685990338164251,
|
| 1218 |
+
"grad_norm": 2.805958882681691,
|
| 1219 |
+
"learning_rate": 2e-05,
|
| 1220 |
+
"loss": 0.7814671993255615,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.0672463768115942,
|
| 1225 |
+
"grad_norm": 8.944621163352808,
|
| 1226 |
+
"learning_rate": 2e-05,
|
| 1227 |
+
"loss": 0.7775825500488281,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.06763285024154589,
|
| 1232 |
+
"grad_norm": 1.3932999773436152,
|
| 1233 |
+
"learning_rate": 2e-05,
|
| 1234 |
+
"loss": 0.813438606262207,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.06801932367149759,
|
| 1239 |
+
"grad_norm": 1.1571499874919873,
|
| 1240 |
+
"learning_rate": 2e-05,
|
| 1241 |
+
"loss": 0.7704301834106445,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.06840579710144927,
|
| 1246 |
+
"grad_norm": 16.767188751455745,
|
| 1247 |
+
"learning_rate": 2e-05,
|
| 1248 |
+
"loss": 0.778882360458374,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.06879227053140097,
|
| 1253 |
+
"grad_norm": 1.8040160227751316,
|
| 1254 |
+
"learning_rate": 2e-05,
|
| 1255 |
+
"loss": 0.7672492980957031,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.06917874396135265,
|
| 1260 |
+
"grad_norm": 1.9003065034750897,
|
| 1261 |
+
"learning_rate": 2e-05,
|
| 1262 |
+
"loss": 0.7559861183166504,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.06956521739130435,
|
| 1267 |
+
"grad_norm": 4.328779850300501,
|
| 1268 |
+
"learning_rate": 2e-05,
|
| 1269 |
+
"loss": 0.7670548439025879,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.06995169082125603,
|
| 1274 |
+
"grad_norm": 1.5009521124497522,
|
| 1275 |
+
"learning_rate": 2e-05,
|
| 1276 |
+
"loss": 0.7466334342956543,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.07033816425120773,
|
| 1281 |
+
"grad_norm": 0.9373529421029959,
|
| 1282 |
+
"learning_rate": 2e-05,
|
| 1283 |
+
"loss": 0.7706023216247558,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.07072463768115941,
|
| 1288 |
+
"grad_norm": 2.5673019538259636,
|
| 1289 |
+
"learning_rate": 2e-05,
|
| 1290 |
+
"loss": 0.7813019752502441,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.07111111111111111,
|
| 1295 |
+
"grad_norm": 10.595792073325587,
|
| 1296 |
+
"learning_rate": 2e-05,
|
| 1297 |
+
"loss": 0.7712044715881348,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.07149758454106281,
|
| 1302 |
+
"grad_norm": 1.4549261759502392,
|
| 1303 |
+
"learning_rate": 2e-05,
|
| 1304 |
+
"loss": 0.7399177551269531,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.07188405797101449,
|
| 1309 |
+
"grad_norm": 1.3679794209107425,
|
| 1310 |
+
"learning_rate": 2e-05,
|
| 1311 |
+
"loss": 0.7697343349456787,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.07227053140096619,
|
| 1316 |
+
"grad_norm": 25.30685684908231,
|
| 1317 |
+
"learning_rate": 2e-05,
|
| 1318 |
+
"loss": 0.7722678661346436,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.07265700483091787,
|
| 1323 |
+
"grad_norm": 5.813362887543927,
|
| 1324 |
+
"learning_rate": 2e-05,
|
| 1325 |
+
"loss": 0.8079950332641601,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.07304347826086957,
|
| 1330 |
+
"grad_norm": 7.55091986778727,
|
| 1331 |
+
"learning_rate": 2e-05,
|
| 1332 |
+
"loss": 0.7749129295349121,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.07342995169082125,
|
| 1337 |
+
"grad_norm": 2.576691425426098,
|
| 1338 |
+
"learning_rate": 2e-05,
|
| 1339 |
+
"loss": 0.7901420593261719,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.07381642512077295,
|
| 1344 |
+
"grad_norm": 2.850989381932755,
|
| 1345 |
+
"learning_rate": 2e-05,
|
| 1346 |
+
"loss": 0.7870397567749023,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.07420289855072464,
|
| 1351 |
+
"grad_norm": 2.8388031664275593,
|
| 1352 |
+
"learning_rate": 2e-05,
|
| 1353 |
+
"loss": 0.798320722579956,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.07458937198067633,
|
| 1358 |
+
"grad_norm": 1.2660870766825572,
|
| 1359 |
+
"learning_rate": 2e-05,
|
| 1360 |
+
"loss": 0.7990159034729004,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.07497584541062802,
|
| 1365 |
+
"grad_norm": 7.521731822457599,
|
| 1366 |
+
"learning_rate": 2e-05,
|
| 1367 |
+
"loss": 0.8066888809204101,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.07536231884057971,
|
| 1372 |
+
"grad_norm": 2.2847479728174886,
|
| 1373 |
+
"learning_rate": 2e-05,
|
| 1374 |
+
"loss": 0.7807460784912109,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.0757487922705314,
|
| 1379 |
+
"grad_norm": 36.52969282187383,
|
| 1380 |
+
"learning_rate": 2e-05,
|
| 1381 |
+
"loss": 0.7917587280273437,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.0761352657004831,
|
| 1386 |
+
"grad_norm": 3.301236759706295,
|
| 1387 |
+
"learning_rate": 2e-05,
|
| 1388 |
+
"loss": 0.7987814903259277,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.07652173913043478,
|
| 1393 |
+
"grad_norm": 2.9129761845971176,
|
| 1394 |
+
"learning_rate": 2e-05,
|
| 1395 |
+
"loss": 0.7681584358215332,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.07690821256038648,
|
| 1400 |
+
"grad_norm": 2.124239464203845,
|
| 1401 |
+
"learning_rate": 2e-05,
|
| 1402 |
+
"loss": 0.7853168487548828,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.07729468599033816,
|
| 1407 |
+
"grad_norm": 6.0767545983301225,
|
| 1408 |
+
"learning_rate": 2e-05,
|
| 1409 |
+
"loss": 0.7794623374938965,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.07768115942028986,
|
| 1414 |
+
"grad_norm": 1.3709998398850736,
|
| 1415 |
+
"learning_rate": 2e-05,
|
| 1416 |
+
"loss": 0.7739840984344483,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.07806763285024154,
|
| 1421 |
+
"grad_norm": 1.5709783521988716,
|
| 1422 |
+
"learning_rate": 2e-05,
|
| 1423 |
+
"loss": 0.7280101776123047,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.07845410628019324,
|
| 1428 |
+
"grad_norm": 2.0426823491051156,
|
| 1429 |
+
"learning_rate": 2e-05,
|
| 1430 |
+
"loss": 0.7502191066741943,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
}
|
| 1433 |
+
],
|
| 1434 |
+
"logging_steps": 10,
|
| 1435 |
+
"max_steps": 5935,
|
| 1436 |
+
"num_input_tokens_seen": 0,
|
| 1437 |
+
"num_train_epochs": 1,
|
| 1438 |
+
"save_steps": 2035,
|
| 1439 |
+
"stateful_callbacks": {
|
| 1440 |
+
"TrainerControl": {
|
| 1441 |
+
"args": {
|
| 1442 |
+
"should_epoch_stop": false,
|
| 1443 |
+
"should_evaluate": false,
|
| 1444 |
+
"should_log": false,
|
| 1445 |
+
"should_save": true,
|
| 1446 |
+
"should_training_stop": false
|
| 1447 |
+
},
|
| 1448 |
+
"attributes": {}
|
| 1449 |
+
}
|
| 1450 |
+
},
|
| 1451 |
+
"total_flos": 963613493821440.0,
|
| 1452 |
+
"train_batch_size": 1,
|
| 1453 |
+
"trial_name": null,
|
| 1454 |
+
"trial_params": null
|
| 1455 |
+
}
|
200M/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce14779932c039c2b5b1ad6f82beb32ebe48924dddeb354b0f0c0746260e210d
|
| 3 |
+
size 7313
|