Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-1000/config.json +47 -0
- checkpoint-1000/generation_config.json +12 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +9 -0
- checkpoint-1000/trainer_state.json +190 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/config.json +47 -0
- checkpoint-1500/generation_config.json +12 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scaler.pt +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer_config.json +9 -0
- checkpoint-1500/trainer_state.json +268 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/config.json +47 -0
- checkpoint-2000/generation_config.json +12 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +9 -0
- checkpoint-2000/trainer_state.json +346 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/config.json +47 -0
- checkpoint-2500/generation_config.json +12 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2500/tokenizer_config.json +9 -0
- checkpoint-2500/trainer_state.json +424 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-3000/config.json +47 -0
- checkpoint-3000/generation_config.json +12 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scaler.pt +3 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_final_layer_norm": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 16384,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 384,
|
| 12 |
+
"decoder_attention_heads": 6,
|
| 13 |
+
"decoder_ffn_dim": 768,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 1,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"dtype": "float32",
|
| 19 |
+
"encoder_attention_heads": 6,
|
| 20 |
+
"encoder_ffn_dim": 768,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 1,
|
| 24 |
+
"forced_eos_token_id": 1,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "LABEL_0",
|
| 27 |
+
"1": "LABEL_1",
|
| 28 |
+
"2": "LABEL_2"
|
| 29 |
+
},
|
| 30 |
+
"init_std": 0.02,
|
| 31 |
+
"is_decoder": false,
|
| 32 |
+
"is_encoder_decoder": true,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1,
|
| 36 |
+
"LABEL_2": 2
|
| 37 |
+
},
|
| 38 |
+
"max_position_embeddings": 128,
|
| 39 |
+
"model_type": "bart",
|
| 40 |
+
"normalize_before": true,
|
| 41 |
+
"pad_token_id": 2,
|
| 42 |
+
"scale_embedding": true,
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "5.9.0",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 16385
|
| 47 |
+
}
|
checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 16384,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 2,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:214e52b8cec413a2d494223e30b967b54cc14cd2aa245cd79ea454a0512f98d6
|
| 3 |
+
size 96704732
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:561978a68a5fd2492305ae7cbf6f36c65c6320f1bd71d1edb9a90f5487d11e9c
|
| 3 |
+
size 193440203
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ffdd85d14ccd416dd8ef96c34f0234941b4d419183e09d27fa4f6edf6c29036
|
| 3 |
+
size 14645
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
|
| 3 |
+
size 1383
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfc5c6949cf8a9eca4d88710f0c9c06f410fb63454fb60c644727889ad457648
|
| 3 |
+
size 1465
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 128,
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3748125937031484,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018740629685157422,
|
| 14 |
+
"grad_norm": 1.3957158327102661,
|
| 15 |
+
"learning_rate": 1.47e-05,
|
| 16 |
+
"loss": 9.729989013671876,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.037481259370314844,
|
| 21 |
+
"grad_norm": 1.4920259714126587,
|
| 22 |
+
"learning_rate": 2.97e-05,
|
| 23 |
+
"loss": 9.0034130859375,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05622188905547226,
|
| 28 |
+
"grad_norm": 1.3049159049987793,
|
| 29 |
+
"learning_rate": 4.4699999999999996e-05,
|
| 30 |
+
"loss": 8.466640014648437,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07496251874062969,
|
| 35 |
+
"grad_norm": 0.8636816740036011,
|
| 36 |
+
"learning_rate": 5.97e-05,
|
| 37 |
+
"loss": 7.869417724609375,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0937031484257871,
|
| 42 |
+
"grad_norm": 0.46240487694740295,
|
| 43 |
+
"learning_rate": 7.47e-05,
|
| 44 |
+
"loss": 7.4413623046875,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11244377811094453,
|
| 49 |
+
"grad_norm": 0.42481327056884766,
|
| 50 |
+
"learning_rate": 8.969999999999998e-05,
|
| 51 |
+
"loss": 7.2437841796875,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13118440779610194,
|
| 56 |
+
"grad_norm": 0.48112183809280396,
|
| 57 |
+
"learning_rate": 0.00010469999999999998,
|
| 58 |
+
"loss": 7.021725463867187,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14992503748125938,
|
| 63 |
+
"grad_norm": 0.4746127724647522,
|
| 64 |
+
"learning_rate": 0.0001197,
|
| 65 |
+
"loss": 6.769576416015625,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1686656671664168,
|
| 70 |
+
"grad_norm": 0.48956719040870667,
|
| 71 |
+
"learning_rate": 0.0001347,
|
| 72 |
+
"loss": 6.538475341796875,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1874062968515742,
|
| 77 |
+
"grad_norm": 0.5688585638999939,
|
| 78 |
+
"learning_rate": 0.00014969999999999998,
|
| 79 |
+
"loss": 6.308619384765625,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1874062968515742,
|
| 84 |
+
"eval_loss": 6.167688369750977,
|
| 85 |
+
"eval_runtime": 1.0817,
|
| 86 |
+
"eval_samples_per_second": 1849.023,
|
| 87 |
+
"eval_steps_per_second": 14.792,
|
| 88 |
+
"step": 500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.20614692653673164,
|
| 92 |
+
"grad_norm": 0.7463164925575256,
|
| 93 |
+
"learning_rate": 0.0001647,
|
| 94 |
+
"loss": 6.135632934570313,
|
| 95 |
+
"step": 550
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.22488755622188905,
|
| 99 |
+
"grad_norm": 0.6867733001708984,
|
| 100 |
+
"learning_rate": 0.00017969999999999998,
|
| 101 |
+
"loss": 5.97782470703125,
|
| 102 |
+
"step": 600
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.2436281859070465,
|
| 106 |
+
"grad_norm": 0.6764475703239441,
|
| 107 |
+
"learning_rate": 0.0001947,
|
| 108 |
+
"loss": 5.829049072265625,
|
| 109 |
+
"step": 650
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2623688155922039,
|
| 113 |
+
"grad_norm": 0.8201554417610168,
|
| 114 |
+
"learning_rate": 0.00020969999999999997,
|
| 115 |
+
"loss": 5.679007568359375,
|
| 116 |
+
"step": 700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2811094452773613,
|
| 120 |
+
"grad_norm": 0.7325769662857056,
|
| 121 |
+
"learning_rate": 0.0002247,
|
| 122 |
+
"loss": 5.54383056640625,
|
| 123 |
+
"step": 750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.29985007496251875,
|
| 127 |
+
"grad_norm": 0.8120824694633484,
|
| 128 |
+
"learning_rate": 0.0002397,
|
| 129 |
+
"loss": 5.398251953125,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.31859070464767614,
|
| 134 |
+
"grad_norm": 0.8338794708251953,
|
| 135 |
+
"learning_rate": 0.00025469999999999996,
|
| 136 |
+
"loss": 5.269853515625,
|
| 137 |
+
"step": 850
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3373313343328336,
|
| 141 |
+
"grad_norm": 0.747706413269043,
|
| 142 |
+
"learning_rate": 0.0002697,
|
| 143 |
+
"loss": 5.1615771484375,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.356071964017991,
|
| 148 |
+
"grad_norm": 1.213719367980957,
|
| 149 |
+
"learning_rate": 0.0002847,
|
| 150 |
+
"loss": 5.037232666015625,
|
| 151 |
+
"step": 950
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3748125937031484,
|
| 155 |
+
"grad_norm": 1.0340992212295532,
|
| 156 |
+
"learning_rate": 0.00029969999999999997,
|
| 157 |
+
"loss": 4.913594055175781,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.3748125937031484,
|
| 162 |
+
"eval_loss": 4.758162021636963,
|
| 163 |
+
"eval_runtime": 1.0759,
|
| 164 |
+
"eval_samples_per_second": 1858.983,
|
| 165 |
+
"eval_steps_per_second": 14.872,
|
| 166 |
+
"step": 1000
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"logging_steps": 50,
|
| 170 |
+
"max_steps": 6000,
|
| 171 |
+
"num_input_tokens_seen": 0,
|
| 172 |
+
"num_train_epochs": 3,
|
| 173 |
+
"save_steps": 500,
|
| 174 |
+
"stateful_callbacks": {
|
| 175 |
+
"TrainerControl": {
|
| 176 |
+
"args": {
|
| 177 |
+
"should_epoch_stop": false,
|
| 178 |
+
"should_evaluate": false,
|
| 179 |
+
"should_log": false,
|
| 180 |
+
"should_save": true,
|
| 181 |
+
"should_training_stop": false
|
| 182 |
+
},
|
| 183 |
+
"attributes": {}
|
| 184 |
+
}
|
| 185 |
+
},
|
| 186 |
+
"total_flos": 726862698381312.0,
|
| 187 |
+
"train_batch_size": 128,
|
| 188 |
+
"trial_name": null,
|
| 189 |
+
"trial_params": null
|
| 190 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee7da759e58ad315e9aab0bd0a67aaf65d967502be17f1c7422afebdd2d3e30
|
| 3 |
+
size 5393
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_final_layer_norm": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 16384,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 384,
|
| 12 |
+
"decoder_attention_heads": 6,
|
| 13 |
+
"decoder_ffn_dim": 768,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 1,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"dtype": "float32",
|
| 19 |
+
"encoder_attention_heads": 6,
|
| 20 |
+
"encoder_ffn_dim": 768,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 1,
|
| 24 |
+
"forced_eos_token_id": 1,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "LABEL_0",
|
| 27 |
+
"1": "LABEL_1",
|
| 28 |
+
"2": "LABEL_2"
|
| 29 |
+
},
|
| 30 |
+
"init_std": 0.02,
|
| 31 |
+
"is_decoder": false,
|
| 32 |
+
"is_encoder_decoder": true,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1,
|
| 36 |
+
"LABEL_2": 2
|
| 37 |
+
},
|
| 38 |
+
"max_position_embeddings": 128,
|
| 39 |
+
"model_type": "bart",
|
| 40 |
+
"normalize_before": true,
|
| 41 |
+
"pad_token_id": 2,
|
| 42 |
+
"scale_embedding": true,
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "5.9.0",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 16385
|
| 47 |
+
}
|
checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 16384,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 2,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2561b9fe67fbbce9ebbf631c5537978bf5af7138c7f9b9863801849c2133ee0
|
| 3 |
+
size 96704732
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9567641cbf1576af6c7e0fbe1a9aa5093557280b0dbaaa097d54b46eb371554
|
| 3 |
+
size 193440203
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2621efea203e4348ed8a17b81a8b647569c0a21dbccf6aa7269a1b3e9d9de0b
|
| 3 |
+
size 14645
|
checkpoint-1500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
|
| 3 |
+
size 1383
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3151a11a1b8b3be551dff2a837b9e022975cdf8dfe701f25f393f58db23e5080
|
| 3 |
+
size 1465
|
checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 128,
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,268 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5622188905547226,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018740629685157422,
|
| 14 |
+
"grad_norm": 1.3957158327102661,
|
| 15 |
+
"learning_rate": 1.47e-05,
|
| 16 |
+
"loss": 9.729989013671876,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.037481259370314844,
|
| 21 |
+
"grad_norm": 1.4920259714126587,
|
| 22 |
+
"learning_rate": 2.97e-05,
|
| 23 |
+
"loss": 9.0034130859375,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05622188905547226,
|
| 28 |
+
"grad_norm": 1.3049159049987793,
|
| 29 |
+
"learning_rate": 4.4699999999999996e-05,
|
| 30 |
+
"loss": 8.466640014648437,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07496251874062969,
|
| 35 |
+
"grad_norm": 0.8636816740036011,
|
| 36 |
+
"learning_rate": 5.97e-05,
|
| 37 |
+
"loss": 7.869417724609375,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0937031484257871,
|
| 42 |
+
"grad_norm": 0.46240487694740295,
|
| 43 |
+
"learning_rate": 7.47e-05,
|
| 44 |
+
"loss": 7.4413623046875,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11244377811094453,
|
| 49 |
+
"grad_norm": 0.42481327056884766,
|
| 50 |
+
"learning_rate": 8.969999999999998e-05,
|
| 51 |
+
"loss": 7.2437841796875,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13118440779610194,
|
| 56 |
+
"grad_norm": 0.48112183809280396,
|
| 57 |
+
"learning_rate": 0.00010469999999999998,
|
| 58 |
+
"loss": 7.021725463867187,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14992503748125938,
|
| 63 |
+
"grad_norm": 0.4746127724647522,
|
| 64 |
+
"learning_rate": 0.0001197,
|
| 65 |
+
"loss": 6.769576416015625,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1686656671664168,
|
| 70 |
+
"grad_norm": 0.48956719040870667,
|
| 71 |
+
"learning_rate": 0.0001347,
|
| 72 |
+
"loss": 6.538475341796875,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1874062968515742,
|
| 77 |
+
"grad_norm": 0.5688585638999939,
|
| 78 |
+
"learning_rate": 0.00014969999999999998,
|
| 79 |
+
"loss": 6.308619384765625,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1874062968515742,
|
| 84 |
+
"eval_loss": 6.167688369750977,
|
| 85 |
+
"eval_runtime": 1.0817,
|
| 86 |
+
"eval_samples_per_second": 1849.023,
|
| 87 |
+
"eval_steps_per_second": 14.792,
|
| 88 |
+
"step": 500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.20614692653673164,
|
| 92 |
+
"grad_norm": 0.7463164925575256,
|
| 93 |
+
"learning_rate": 0.0001647,
|
| 94 |
+
"loss": 6.135632934570313,
|
| 95 |
+
"step": 550
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.22488755622188905,
|
| 99 |
+
"grad_norm": 0.6867733001708984,
|
| 100 |
+
"learning_rate": 0.00017969999999999998,
|
| 101 |
+
"loss": 5.97782470703125,
|
| 102 |
+
"step": 600
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.2436281859070465,
|
| 106 |
+
"grad_norm": 0.6764475703239441,
|
| 107 |
+
"learning_rate": 0.0001947,
|
| 108 |
+
"loss": 5.829049072265625,
|
| 109 |
+
"step": 650
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2623688155922039,
|
| 113 |
+
"grad_norm": 0.8201554417610168,
|
| 114 |
+
"learning_rate": 0.00020969999999999997,
|
| 115 |
+
"loss": 5.679007568359375,
|
| 116 |
+
"step": 700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2811094452773613,
|
| 120 |
+
"grad_norm": 0.7325769662857056,
|
| 121 |
+
"learning_rate": 0.0002247,
|
| 122 |
+
"loss": 5.54383056640625,
|
| 123 |
+
"step": 750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.29985007496251875,
|
| 127 |
+
"grad_norm": 0.8120824694633484,
|
| 128 |
+
"learning_rate": 0.0002397,
|
| 129 |
+
"loss": 5.398251953125,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.31859070464767614,
|
| 134 |
+
"grad_norm": 0.8338794708251953,
|
| 135 |
+
"learning_rate": 0.00025469999999999996,
|
| 136 |
+
"loss": 5.269853515625,
|
| 137 |
+
"step": 850
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3373313343328336,
|
| 141 |
+
"grad_norm": 0.747706413269043,
|
| 142 |
+
"learning_rate": 0.0002697,
|
| 143 |
+
"loss": 5.1615771484375,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.356071964017991,
|
| 148 |
+
"grad_norm": 1.213719367980957,
|
| 149 |
+
"learning_rate": 0.0002847,
|
| 150 |
+
"loss": 5.037232666015625,
|
| 151 |
+
"step": 950
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3748125937031484,
|
| 155 |
+
"grad_norm": 1.0340992212295532,
|
| 156 |
+
"learning_rate": 0.00029969999999999997,
|
| 157 |
+
"loss": 4.913594055175781,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.3748125937031484,
|
| 162 |
+
"eval_loss": 4.758162021636963,
|
| 163 |
+
"eval_runtime": 1.0759,
|
| 164 |
+
"eval_samples_per_second": 1858.983,
|
| 165 |
+
"eval_steps_per_second": 14.872,
|
| 166 |
+
"step": 1000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.39355322338830584,
|
| 170 |
+
"grad_norm": 0.8748279809951782,
|
| 171 |
+
"learning_rate": 0.00029706,
|
| 172 |
+
"loss": 4.810666809082031,
|
| 173 |
+
"step": 1050
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.4122938530734633,
|
| 177 |
+
"grad_norm": 0.8297407031059265,
|
| 178 |
+
"learning_rate": 0.00029405999999999996,
|
| 179 |
+
"loss": 4.683534851074219,
|
| 180 |
+
"step": 1100
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.43103448275862066,
|
| 184 |
+
"grad_norm": 0.9721106290817261,
|
| 185 |
+
"learning_rate": 0.00029105999999999994,
|
| 186 |
+
"loss": 4.601776733398437,
|
| 187 |
+
"step": 1150
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.4497751124437781,
|
| 191 |
+
"grad_norm": 0.9634228348731995,
|
| 192 |
+
"learning_rate": 0.00028806,
|
| 193 |
+
"loss": 4.503483581542969,
|
| 194 |
+
"step": 1200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46851574212893554,
|
| 198 |
+
"grad_norm": 1.0372576713562012,
|
| 199 |
+
"learning_rate": 0.00028506,
|
| 200 |
+
"loss": 4.401589050292968,
|
| 201 |
+
"step": 1250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.487256371814093,
|
| 205 |
+
"grad_norm": 1.0020194053649902,
|
| 206 |
+
"learning_rate": 0.00028206,
|
| 207 |
+
"loss": 4.325810546875,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.5059970014992504,
|
| 212 |
+
"grad_norm": 0.969415545463562,
|
| 213 |
+
"learning_rate": 0.00027906,
|
| 214 |
+
"loss": 4.261092834472656,
|
| 215 |
+
"step": 1350
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5247376311844077,
|
| 219 |
+
"grad_norm": 1.1663305759429932,
|
| 220 |
+
"learning_rate": 0.00027605999999999996,
|
| 221 |
+
"loss": 4.167784423828125,
|
| 222 |
+
"step": 1400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5434782608695652,
|
| 226 |
+
"grad_norm": 1.0733853578567505,
|
| 227 |
+
"learning_rate": 0.00027306,
|
| 228 |
+
"loss": 4.096864624023437,
|
| 229 |
+
"step": 1450
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5622188905547226,
|
| 233 |
+
"grad_norm": 1.0118414163589478,
|
| 234 |
+
"learning_rate": 0.00027005999999999997,
|
| 235 |
+
"loss": 4.057973937988281,
|
| 236 |
+
"step": 1500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.5622188905547226,
|
| 240 |
+
"eval_loss": 3.895841121673584,
|
| 241 |
+
"eval_runtime": 1.0897,
|
| 242 |
+
"eval_samples_per_second": 1835.392,
|
| 243 |
+
"eval_steps_per_second": 14.683,
|
| 244 |
+
"step": 1500
|
| 245 |
+
}
|
| 246 |
+
],
|
| 247 |
+
"logging_steps": 50,
|
| 248 |
+
"max_steps": 6000,
|
| 249 |
+
"num_input_tokens_seen": 0,
|
| 250 |
+
"num_train_epochs": 3,
|
| 251 |
+
"save_steps": 500,
|
| 252 |
+
"stateful_callbacks": {
|
| 253 |
+
"TrainerControl": {
|
| 254 |
+
"args": {
|
| 255 |
+
"should_epoch_stop": false,
|
| 256 |
+
"should_evaluate": false,
|
| 257 |
+
"should_log": false,
|
| 258 |
+
"should_save": true,
|
| 259 |
+
"should_training_stop": false
|
| 260 |
+
},
|
| 261 |
+
"attributes": {}
|
| 262 |
+
}
|
| 263 |
+
},
|
| 264 |
+
"total_flos": 1090321328111616.0,
|
| 265 |
+
"train_batch_size": 128,
|
| 266 |
+
"trial_name": null,
|
| 267 |
+
"trial_params": null
|
| 268 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee7da759e58ad315e9aab0bd0a67aaf65d967502be17f1c7422afebdd2d3e30
|
| 3 |
+
size 5393
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_final_layer_norm": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 16384,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 384,
|
| 12 |
+
"decoder_attention_heads": 6,
|
| 13 |
+
"decoder_ffn_dim": 768,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 1,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"dtype": "float32",
|
| 19 |
+
"encoder_attention_heads": 6,
|
| 20 |
+
"encoder_ffn_dim": 768,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 1,
|
| 24 |
+
"forced_eos_token_id": 1,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "LABEL_0",
|
| 27 |
+
"1": "LABEL_1",
|
| 28 |
+
"2": "LABEL_2"
|
| 29 |
+
},
|
| 30 |
+
"init_std": 0.02,
|
| 31 |
+
"is_decoder": false,
|
| 32 |
+
"is_encoder_decoder": true,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1,
|
| 36 |
+
"LABEL_2": 2
|
| 37 |
+
},
|
| 38 |
+
"max_position_embeddings": 128,
|
| 39 |
+
"model_type": "bart",
|
| 40 |
+
"normalize_before": true,
|
| 41 |
+
"pad_token_id": 2,
|
| 42 |
+
"scale_embedding": true,
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "5.9.0",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 16385
|
| 47 |
+
}
|
checkpoint-2000/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 16384,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 2,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aa34006930413e0be9aeadc09140f225a17d8fd68c70b4eb67688afc6e6d489
|
| 3 |
+
size 96704732
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:078915e0181f4f013227a3c298e1ae1fec1ecc9511ffee25c1e6394ead1e62ec
|
| 3 |
+
size 193440203
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eba28bd0b5bf25c675aa4d94eb77544e84a6e54cc59510591506c783627b564
|
| 3 |
+
size 14645
|
checkpoint-2000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
|
| 3 |
+
size 1383
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4066bef9a57d5bae50e314a302f6b9b5ab3c08dab487b5340a24e8b18f98d40d
|
| 3 |
+
size 1465
|
checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 128,
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7496251874062968,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018740629685157422,
|
| 14 |
+
"grad_norm": 1.3957158327102661,
|
| 15 |
+
"learning_rate": 1.47e-05,
|
| 16 |
+
"loss": 9.729989013671876,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.037481259370314844,
|
| 21 |
+
"grad_norm": 1.4920259714126587,
|
| 22 |
+
"learning_rate": 2.97e-05,
|
| 23 |
+
"loss": 9.0034130859375,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05622188905547226,
|
| 28 |
+
"grad_norm": 1.3049159049987793,
|
| 29 |
+
"learning_rate": 4.4699999999999996e-05,
|
| 30 |
+
"loss": 8.466640014648437,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07496251874062969,
|
| 35 |
+
"grad_norm": 0.8636816740036011,
|
| 36 |
+
"learning_rate": 5.97e-05,
|
| 37 |
+
"loss": 7.869417724609375,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0937031484257871,
|
| 42 |
+
"grad_norm": 0.46240487694740295,
|
| 43 |
+
"learning_rate": 7.47e-05,
|
| 44 |
+
"loss": 7.4413623046875,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11244377811094453,
|
| 49 |
+
"grad_norm": 0.42481327056884766,
|
| 50 |
+
"learning_rate": 8.969999999999998e-05,
|
| 51 |
+
"loss": 7.2437841796875,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13118440779610194,
|
| 56 |
+
"grad_norm": 0.48112183809280396,
|
| 57 |
+
"learning_rate": 0.00010469999999999998,
|
| 58 |
+
"loss": 7.021725463867187,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14992503748125938,
|
| 63 |
+
"grad_norm": 0.4746127724647522,
|
| 64 |
+
"learning_rate": 0.0001197,
|
| 65 |
+
"loss": 6.769576416015625,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1686656671664168,
|
| 70 |
+
"grad_norm": 0.48956719040870667,
|
| 71 |
+
"learning_rate": 0.0001347,
|
| 72 |
+
"loss": 6.538475341796875,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1874062968515742,
|
| 77 |
+
"grad_norm": 0.5688585638999939,
|
| 78 |
+
"learning_rate": 0.00014969999999999998,
|
| 79 |
+
"loss": 6.308619384765625,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1874062968515742,
|
| 84 |
+
"eval_loss": 6.167688369750977,
|
| 85 |
+
"eval_runtime": 1.0817,
|
| 86 |
+
"eval_samples_per_second": 1849.023,
|
| 87 |
+
"eval_steps_per_second": 14.792,
|
| 88 |
+
"step": 500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.20614692653673164,
|
| 92 |
+
"grad_norm": 0.7463164925575256,
|
| 93 |
+
"learning_rate": 0.0001647,
|
| 94 |
+
"loss": 6.135632934570313,
|
| 95 |
+
"step": 550
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.22488755622188905,
|
| 99 |
+
"grad_norm": 0.6867733001708984,
|
| 100 |
+
"learning_rate": 0.00017969999999999998,
|
| 101 |
+
"loss": 5.97782470703125,
|
| 102 |
+
"step": 600
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.2436281859070465,
|
| 106 |
+
"grad_norm": 0.6764475703239441,
|
| 107 |
+
"learning_rate": 0.0001947,
|
| 108 |
+
"loss": 5.829049072265625,
|
| 109 |
+
"step": 650
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2623688155922039,
|
| 113 |
+
"grad_norm": 0.8201554417610168,
|
| 114 |
+
"learning_rate": 0.00020969999999999997,
|
| 115 |
+
"loss": 5.679007568359375,
|
| 116 |
+
"step": 700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2811094452773613,
|
| 120 |
+
"grad_norm": 0.7325769662857056,
|
| 121 |
+
"learning_rate": 0.0002247,
|
| 122 |
+
"loss": 5.54383056640625,
|
| 123 |
+
"step": 750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.29985007496251875,
|
| 127 |
+
"grad_norm": 0.8120824694633484,
|
| 128 |
+
"learning_rate": 0.0002397,
|
| 129 |
+
"loss": 5.398251953125,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.31859070464767614,
|
| 134 |
+
"grad_norm": 0.8338794708251953,
|
| 135 |
+
"learning_rate": 0.00025469999999999996,
|
| 136 |
+
"loss": 5.269853515625,
|
| 137 |
+
"step": 850
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3373313343328336,
|
| 141 |
+
"grad_norm": 0.747706413269043,
|
| 142 |
+
"learning_rate": 0.0002697,
|
| 143 |
+
"loss": 5.1615771484375,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.356071964017991,
|
| 148 |
+
"grad_norm": 1.213719367980957,
|
| 149 |
+
"learning_rate": 0.0002847,
|
| 150 |
+
"loss": 5.037232666015625,
|
| 151 |
+
"step": 950
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3748125937031484,
|
| 155 |
+
"grad_norm": 1.0340992212295532,
|
| 156 |
+
"learning_rate": 0.00029969999999999997,
|
| 157 |
+
"loss": 4.913594055175781,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.3748125937031484,
|
| 162 |
+
"eval_loss": 4.758162021636963,
|
| 163 |
+
"eval_runtime": 1.0759,
|
| 164 |
+
"eval_samples_per_second": 1858.983,
|
| 165 |
+
"eval_steps_per_second": 14.872,
|
| 166 |
+
"step": 1000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.39355322338830584,
|
| 170 |
+
"grad_norm": 0.8748279809951782,
|
| 171 |
+
"learning_rate": 0.00029706,
|
| 172 |
+
"loss": 4.810666809082031,
|
| 173 |
+
"step": 1050
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.4122938530734633,
|
| 177 |
+
"grad_norm": 0.8297407031059265,
|
| 178 |
+
"learning_rate": 0.00029405999999999996,
|
| 179 |
+
"loss": 4.683534851074219,
|
| 180 |
+
"step": 1100
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.43103448275862066,
|
| 184 |
+
"grad_norm": 0.9721106290817261,
|
| 185 |
+
"learning_rate": 0.00029105999999999994,
|
| 186 |
+
"loss": 4.601776733398437,
|
| 187 |
+
"step": 1150
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.4497751124437781,
|
| 191 |
+
"grad_norm": 0.9634228348731995,
|
| 192 |
+
"learning_rate": 0.00028806,
|
| 193 |
+
"loss": 4.503483581542969,
|
| 194 |
+
"step": 1200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46851574212893554,
|
| 198 |
+
"grad_norm": 1.0372576713562012,
|
| 199 |
+
"learning_rate": 0.00028506,
|
| 200 |
+
"loss": 4.401589050292968,
|
| 201 |
+
"step": 1250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.487256371814093,
|
| 205 |
+
"grad_norm": 1.0020194053649902,
|
| 206 |
+
"learning_rate": 0.00028206,
|
| 207 |
+
"loss": 4.325810546875,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.5059970014992504,
|
| 212 |
+
"grad_norm": 0.969415545463562,
|
| 213 |
+
"learning_rate": 0.00027906,
|
| 214 |
+
"loss": 4.261092834472656,
|
| 215 |
+
"step": 1350
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5247376311844077,
|
| 219 |
+
"grad_norm": 1.1663305759429932,
|
| 220 |
+
"learning_rate": 0.00027605999999999996,
|
| 221 |
+
"loss": 4.167784423828125,
|
| 222 |
+
"step": 1400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5434782608695652,
|
| 226 |
+
"grad_norm": 1.0733853578567505,
|
| 227 |
+
"learning_rate": 0.00027306,
|
| 228 |
+
"loss": 4.096864624023437,
|
| 229 |
+
"step": 1450
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5622188905547226,
|
| 233 |
+
"grad_norm": 1.0118414163589478,
|
| 234 |
+
"learning_rate": 0.00027005999999999997,
|
| 235 |
+
"loss": 4.057973937988281,
|
| 236 |
+
"step": 1500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.5622188905547226,
|
| 240 |
+
"eval_loss": 3.895841121673584,
|
| 241 |
+
"eval_runtime": 1.0897,
|
| 242 |
+
"eval_samples_per_second": 1835.392,
|
| 243 |
+
"eval_steps_per_second": 14.683,
|
| 244 |
+
"step": 1500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.5809595202398801,
|
| 248 |
+
"grad_norm": 0.9456564784049988,
|
| 249 |
+
"learning_rate": 0.00026705999999999995,
|
| 250 |
+
"loss": 3.999591064453125,
|
| 251 |
+
"step": 1550
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.5997001499250375,
|
| 255 |
+
"grad_norm": 1.0527812242507935,
|
| 256 |
+
"learning_rate": 0.00026406,
|
| 257 |
+
"loss": 3.928629150390625,
|
| 258 |
+
"step": 1600
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.618440779610195,
|
| 262 |
+
"grad_norm": 0.9593741297721863,
|
| 263 |
+
"learning_rate": 0.00026105999999999997,
|
| 264 |
+
"loss": 3.86834228515625,
|
| 265 |
+
"step": 1650
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.6371814092953523,
|
| 269 |
+
"grad_norm": 1.0123467445373535,
|
| 270 |
+
"learning_rate": 0.00025805999999999995,
|
| 271 |
+
"loss": 3.8236553955078123,
|
| 272 |
+
"step": 1700
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.6559220389805097,
|
| 276 |
+
"grad_norm": 1.0930705070495605,
|
| 277 |
+
"learning_rate": 0.00025506,
|
| 278 |
+
"loss": 3.7675225830078123,
|
| 279 |
+
"step": 1750
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6746626686656672,
|
| 283 |
+
"grad_norm": 1.2183789014816284,
|
| 284 |
+
"learning_rate": 0.00025205999999999997,
|
| 285 |
+
"loss": 3.722022705078125,
|
| 286 |
+
"step": 1800
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.6934032983508246,
|
| 290 |
+
"grad_norm": 1.1733542680740356,
|
| 291 |
+
"learning_rate": 0.00024906,
|
| 292 |
+
"loss": 3.6782516479492187,
|
| 293 |
+
"step": 1850
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.712143928035982,
|
| 297 |
+
"grad_norm": 1.1061464548110962,
|
| 298 |
+
"learning_rate": 0.00024606,
|
| 299 |
+
"loss": 3.6340737915039063,
|
| 300 |
+
"step": 1900
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.7308845577211395,
|
| 304 |
+
"grad_norm": 1.1385581493377686,
|
| 305 |
+
"learning_rate": 0.00024306,
|
| 306 |
+
"loss": 3.596466369628906,
|
| 307 |
+
"step": 1950
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.7496251874062968,
|
| 311 |
+
"grad_norm": 1.2214317321777344,
|
| 312 |
+
"learning_rate": 0.00024005999999999998,
|
| 313 |
+
"loss": 3.5506155395507815,
|
| 314 |
+
"step": 2000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.7496251874062968,
|
| 318 |
+
"eval_loss": 3.386573553085327,
|
| 319 |
+
"eval_runtime": 1.0773,
|
| 320 |
+
"eval_samples_per_second": 1856.47,
|
| 321 |
+
"eval_steps_per_second": 14.852,
|
| 322 |
+
"step": 2000
|
| 323 |
+
}
|
| 324 |
+
],
|
| 325 |
+
"logging_steps": 50,
|
| 326 |
+
"max_steps": 6000,
|
| 327 |
+
"num_input_tokens_seen": 0,
|
| 328 |
+
"num_train_epochs": 3,
|
| 329 |
+
"save_steps": 500,
|
| 330 |
+
"stateful_callbacks": {
|
| 331 |
+
"TrainerControl": {
|
| 332 |
+
"args": {
|
| 333 |
+
"should_epoch_stop": false,
|
| 334 |
+
"should_evaluate": false,
|
| 335 |
+
"should_log": false,
|
| 336 |
+
"should_save": true,
|
| 337 |
+
"should_training_stop": false
|
| 338 |
+
},
|
| 339 |
+
"attributes": {}
|
| 340 |
+
}
|
| 341 |
+
},
|
| 342 |
+
"total_flos": 1454393769984000.0,
|
| 343 |
+
"train_batch_size": 128,
|
| 344 |
+
"trial_name": null,
|
| 345 |
+
"trial_params": null
|
| 346 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee7da759e58ad315e9aab0bd0a67aaf65d967502be17f1c7422afebdd2d3e30
|
| 3 |
+
size 5393
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_final_layer_norm": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 16384,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 384,
|
| 12 |
+
"decoder_attention_heads": 6,
|
| 13 |
+
"decoder_ffn_dim": 768,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 1,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"dtype": "float32",
|
| 19 |
+
"encoder_attention_heads": 6,
|
| 20 |
+
"encoder_ffn_dim": 768,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 1,
|
| 24 |
+
"forced_eos_token_id": 1,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "LABEL_0",
|
| 27 |
+
"1": "LABEL_1",
|
| 28 |
+
"2": "LABEL_2"
|
| 29 |
+
},
|
| 30 |
+
"init_std": 0.02,
|
| 31 |
+
"is_decoder": false,
|
| 32 |
+
"is_encoder_decoder": true,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1,
|
| 36 |
+
"LABEL_2": 2
|
| 37 |
+
},
|
| 38 |
+
"max_position_embeddings": 128,
|
| 39 |
+
"model_type": "bart",
|
| 40 |
+
"normalize_before": true,
|
| 41 |
+
"pad_token_id": 2,
|
| 42 |
+
"scale_embedding": true,
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "5.9.0",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 16385
|
| 47 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 16384,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 2,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c95bb3f098df2801cd32e403ed2b5c7723316790672abadca7e221a705c6e16
|
| 3 |
+
size 96704732
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e55e21d6b2be45298df351148f03544350c52f99a8c7bc93d14f2387a637635
|
| 3 |
+
size 193440203
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc9fe72371164ea9896467921a98ed2fe6f83016371c1b4b8819aec165016cf0
|
| 3 |
+
size 14645
|
checkpoint-2500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:861ce13e6ca091acee9a68ebfc5ca38479baf4b537c37b3949f071f77b81e9f0
|
| 3 |
+
size 1383
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90f825c1b16419ac0b9996424f0f23e3abc4b7985f6fe3bd1f2a566d7b02169d
|
| 3 |
+
size 1465
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 128,
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9370314842578711,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018740629685157422,
|
| 14 |
+
"grad_norm": 1.3957158327102661,
|
| 15 |
+
"learning_rate": 1.47e-05,
|
| 16 |
+
"loss": 9.729989013671876,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.037481259370314844,
|
| 21 |
+
"grad_norm": 1.4920259714126587,
|
| 22 |
+
"learning_rate": 2.97e-05,
|
| 23 |
+
"loss": 9.0034130859375,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05622188905547226,
|
| 28 |
+
"grad_norm": 1.3049159049987793,
|
| 29 |
+
"learning_rate": 4.4699999999999996e-05,
|
| 30 |
+
"loss": 8.466640014648437,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07496251874062969,
|
| 35 |
+
"grad_norm": 0.8636816740036011,
|
| 36 |
+
"learning_rate": 5.97e-05,
|
| 37 |
+
"loss": 7.869417724609375,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0937031484257871,
|
| 42 |
+
"grad_norm": 0.46240487694740295,
|
| 43 |
+
"learning_rate": 7.47e-05,
|
| 44 |
+
"loss": 7.4413623046875,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11244377811094453,
|
| 49 |
+
"grad_norm": 0.42481327056884766,
|
| 50 |
+
"learning_rate": 8.969999999999998e-05,
|
| 51 |
+
"loss": 7.2437841796875,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13118440779610194,
|
| 56 |
+
"grad_norm": 0.48112183809280396,
|
| 57 |
+
"learning_rate": 0.00010469999999999998,
|
| 58 |
+
"loss": 7.021725463867187,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14992503748125938,
|
| 63 |
+
"grad_norm": 0.4746127724647522,
|
| 64 |
+
"learning_rate": 0.0001197,
|
| 65 |
+
"loss": 6.769576416015625,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1686656671664168,
|
| 70 |
+
"grad_norm": 0.48956719040870667,
|
| 71 |
+
"learning_rate": 0.0001347,
|
| 72 |
+
"loss": 6.538475341796875,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1874062968515742,
|
| 77 |
+
"grad_norm": 0.5688585638999939,
|
| 78 |
+
"learning_rate": 0.00014969999999999998,
|
| 79 |
+
"loss": 6.308619384765625,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1874062968515742,
|
| 84 |
+
"eval_loss": 6.167688369750977,
|
| 85 |
+
"eval_runtime": 1.0817,
|
| 86 |
+
"eval_samples_per_second": 1849.023,
|
| 87 |
+
"eval_steps_per_second": 14.792,
|
| 88 |
+
"step": 500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.20614692653673164,
|
| 92 |
+
"grad_norm": 0.7463164925575256,
|
| 93 |
+
"learning_rate": 0.0001647,
|
| 94 |
+
"loss": 6.135632934570313,
|
| 95 |
+
"step": 550
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.22488755622188905,
|
| 99 |
+
"grad_norm": 0.6867733001708984,
|
| 100 |
+
"learning_rate": 0.00017969999999999998,
|
| 101 |
+
"loss": 5.97782470703125,
|
| 102 |
+
"step": 600
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.2436281859070465,
|
| 106 |
+
"grad_norm": 0.6764475703239441,
|
| 107 |
+
"learning_rate": 0.0001947,
|
| 108 |
+
"loss": 5.829049072265625,
|
| 109 |
+
"step": 650
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2623688155922039,
|
| 113 |
+
"grad_norm": 0.8201554417610168,
|
| 114 |
+
"learning_rate": 0.00020969999999999997,
|
| 115 |
+
"loss": 5.679007568359375,
|
| 116 |
+
"step": 700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2811094452773613,
|
| 120 |
+
"grad_norm": 0.7325769662857056,
|
| 121 |
+
"learning_rate": 0.0002247,
|
| 122 |
+
"loss": 5.54383056640625,
|
| 123 |
+
"step": 750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.29985007496251875,
|
| 127 |
+
"grad_norm": 0.8120824694633484,
|
| 128 |
+
"learning_rate": 0.0002397,
|
| 129 |
+
"loss": 5.398251953125,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.31859070464767614,
|
| 134 |
+
"grad_norm": 0.8338794708251953,
|
| 135 |
+
"learning_rate": 0.00025469999999999996,
|
| 136 |
+
"loss": 5.269853515625,
|
| 137 |
+
"step": 850
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3373313343328336,
|
| 141 |
+
"grad_norm": 0.747706413269043,
|
| 142 |
+
"learning_rate": 0.0002697,
|
| 143 |
+
"loss": 5.1615771484375,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.356071964017991,
|
| 148 |
+
"grad_norm": 1.213719367980957,
|
| 149 |
+
"learning_rate": 0.0002847,
|
| 150 |
+
"loss": 5.037232666015625,
|
| 151 |
+
"step": 950
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3748125937031484,
|
| 155 |
+
"grad_norm": 1.0340992212295532,
|
| 156 |
+
"learning_rate": 0.00029969999999999997,
|
| 157 |
+
"loss": 4.913594055175781,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.3748125937031484,
|
| 162 |
+
"eval_loss": 4.758162021636963,
|
| 163 |
+
"eval_runtime": 1.0759,
|
| 164 |
+
"eval_samples_per_second": 1858.983,
|
| 165 |
+
"eval_steps_per_second": 14.872,
|
| 166 |
+
"step": 1000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.39355322338830584,
|
| 170 |
+
"grad_norm": 0.8748279809951782,
|
| 171 |
+
"learning_rate": 0.00029706,
|
| 172 |
+
"loss": 4.810666809082031,
|
| 173 |
+
"step": 1050
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.4122938530734633,
|
| 177 |
+
"grad_norm": 0.8297407031059265,
|
| 178 |
+
"learning_rate": 0.00029405999999999996,
|
| 179 |
+
"loss": 4.683534851074219,
|
| 180 |
+
"step": 1100
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.43103448275862066,
|
| 184 |
+
"grad_norm": 0.9721106290817261,
|
| 185 |
+
"learning_rate": 0.00029105999999999994,
|
| 186 |
+
"loss": 4.601776733398437,
|
| 187 |
+
"step": 1150
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.4497751124437781,
|
| 191 |
+
"grad_norm": 0.9634228348731995,
|
| 192 |
+
"learning_rate": 0.00028806,
|
| 193 |
+
"loss": 4.503483581542969,
|
| 194 |
+
"step": 1200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46851574212893554,
|
| 198 |
+
"grad_norm": 1.0372576713562012,
|
| 199 |
+
"learning_rate": 0.00028506,
|
| 200 |
+
"loss": 4.401589050292968,
|
| 201 |
+
"step": 1250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.487256371814093,
|
| 205 |
+
"grad_norm": 1.0020194053649902,
|
| 206 |
+
"learning_rate": 0.00028206,
|
| 207 |
+
"loss": 4.325810546875,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.5059970014992504,
|
| 212 |
+
"grad_norm": 0.969415545463562,
|
| 213 |
+
"learning_rate": 0.00027906,
|
| 214 |
+
"loss": 4.261092834472656,
|
| 215 |
+
"step": 1350
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5247376311844077,
|
| 219 |
+
"grad_norm": 1.1663305759429932,
|
| 220 |
+
"learning_rate": 0.00027605999999999996,
|
| 221 |
+
"loss": 4.167784423828125,
|
| 222 |
+
"step": 1400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5434782608695652,
|
| 226 |
+
"grad_norm": 1.0733853578567505,
|
| 227 |
+
"learning_rate": 0.00027306,
|
| 228 |
+
"loss": 4.096864624023437,
|
| 229 |
+
"step": 1450
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5622188905547226,
|
| 233 |
+
"grad_norm": 1.0118414163589478,
|
| 234 |
+
"learning_rate": 0.00027005999999999997,
|
| 235 |
+
"loss": 4.057973937988281,
|
| 236 |
+
"step": 1500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.5622188905547226,
|
| 240 |
+
"eval_loss": 3.895841121673584,
|
| 241 |
+
"eval_runtime": 1.0897,
|
| 242 |
+
"eval_samples_per_second": 1835.392,
|
| 243 |
+
"eval_steps_per_second": 14.683,
|
| 244 |
+
"step": 1500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.5809595202398801,
|
| 248 |
+
"grad_norm": 0.9456564784049988,
|
| 249 |
+
"learning_rate": 0.00026705999999999995,
|
| 250 |
+
"loss": 3.999591064453125,
|
| 251 |
+
"step": 1550
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.5997001499250375,
|
| 255 |
+
"grad_norm": 1.0527812242507935,
|
| 256 |
+
"learning_rate": 0.00026406,
|
| 257 |
+
"loss": 3.928629150390625,
|
| 258 |
+
"step": 1600
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.618440779610195,
|
| 262 |
+
"grad_norm": 0.9593741297721863,
|
| 263 |
+
"learning_rate": 0.00026105999999999997,
|
| 264 |
+
"loss": 3.86834228515625,
|
| 265 |
+
"step": 1650
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.6371814092953523,
|
| 269 |
+
"grad_norm": 1.0123467445373535,
|
| 270 |
+
"learning_rate": 0.00025805999999999995,
|
| 271 |
+
"loss": 3.8236553955078123,
|
| 272 |
+
"step": 1700
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.6559220389805097,
|
| 276 |
+
"grad_norm": 1.0930705070495605,
|
| 277 |
+
"learning_rate": 0.00025506,
|
| 278 |
+
"loss": 3.7675225830078123,
|
| 279 |
+
"step": 1750
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6746626686656672,
|
| 283 |
+
"grad_norm": 1.2183789014816284,
|
| 284 |
+
"learning_rate": 0.00025205999999999997,
|
| 285 |
+
"loss": 3.722022705078125,
|
| 286 |
+
"step": 1800
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.6934032983508246,
|
| 290 |
+
"grad_norm": 1.1733542680740356,
|
| 291 |
+
"learning_rate": 0.00024906,
|
| 292 |
+
"loss": 3.6782516479492187,
|
| 293 |
+
"step": 1850
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.712143928035982,
|
| 297 |
+
"grad_norm": 1.1061464548110962,
|
| 298 |
+
"learning_rate": 0.00024606,
|
| 299 |
+
"loss": 3.6340737915039063,
|
| 300 |
+
"step": 1900
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.7308845577211395,
|
| 304 |
+
"grad_norm": 1.1385581493377686,
|
| 305 |
+
"learning_rate": 0.00024306,
|
| 306 |
+
"loss": 3.596466369628906,
|
| 307 |
+
"step": 1950
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.7496251874062968,
|
| 311 |
+
"grad_norm": 1.2214317321777344,
|
| 312 |
+
"learning_rate": 0.00024005999999999998,
|
| 313 |
+
"loss": 3.5506155395507815,
|
| 314 |
+
"step": 2000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.7496251874062968,
|
| 318 |
+
"eval_loss": 3.386573553085327,
|
| 319 |
+
"eval_runtime": 1.0773,
|
| 320 |
+
"eval_samples_per_second": 1856.47,
|
| 321 |
+
"eval_steps_per_second": 14.852,
|
| 322 |
+
"step": 2000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.7683658170914542,
|
| 326 |
+
"grad_norm": 1.081070899963379,
|
| 327 |
+
"learning_rate": 0.00023705999999999998,
|
| 328 |
+
"loss": 3.540574951171875,
|
| 329 |
+
"step": 2050
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.7871064467766117,
|
| 333 |
+
"grad_norm": 1.143646001815796,
|
| 334 |
+
"learning_rate": 0.00023406,
|
| 335 |
+
"loss": 3.496670837402344,
|
| 336 |
+
"step": 2100
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.8058470764617691,
|
| 340 |
+
"grad_norm": 1.1834206581115723,
|
| 341 |
+
"learning_rate": 0.00023105999999999997,
|
| 342 |
+
"loss": 3.4573333740234373,
|
| 343 |
+
"step": 2150
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.8245877061469266,
|
| 347 |
+
"grad_norm": 1.1659979820251465,
|
| 348 |
+
"learning_rate": 0.00022805999999999998,
|
| 349 |
+
"loss": 3.454217529296875,
|
| 350 |
+
"step": 2200
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.843328335832084,
|
| 354 |
+
"grad_norm": 1.1012392044067383,
|
| 355 |
+
"learning_rate": 0.00022505999999999996,
|
| 356 |
+
"loss": 3.410209045410156,
|
| 357 |
+
"step": 2250
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.8620689655172413,
|
| 361 |
+
"grad_norm": 1.1149102449417114,
|
| 362 |
+
"learning_rate": 0.00022205999999999997,
|
| 363 |
+
"loss": 3.3710055541992188,
|
| 364 |
+
"step": 2300
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.8808095952023988,
|
| 368 |
+
"grad_norm": 1.164297103881836,
|
| 369 |
+
"learning_rate": 0.00021905999999999998,
|
| 370 |
+
"loss": 3.3450372314453123,
|
| 371 |
+
"step": 2350
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.8995502248875562,
|
| 375 |
+
"grad_norm": 1.15338933467865,
|
| 376 |
+
"learning_rate": 0.00021605999999999996,
|
| 377 |
+
"loss": 3.318499755859375,
|
| 378 |
+
"step": 2400
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.9182908545727136,
|
| 382 |
+
"grad_norm": 1.1890783309936523,
|
| 383 |
+
"learning_rate": 0.00021306,
|
| 384 |
+
"loss": 3.288759460449219,
|
| 385 |
+
"step": 2450
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.9370314842578711,
|
| 389 |
+
"grad_norm": 1.1333503723144531,
|
| 390 |
+
"learning_rate": 0.00021006,
|
| 391 |
+
"loss": 3.2676837158203127,
|
| 392 |
+
"step": 2500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.9370314842578711,
|
| 396 |
+
"eval_loss": 3.1189351081848145,
|
| 397 |
+
"eval_runtime": 1.0777,
|
| 398 |
+
"eval_samples_per_second": 1855.782,
|
| 399 |
+
"eval_steps_per_second": 14.846,
|
| 400 |
+
"step": 2500
|
| 401 |
+
}
|
| 402 |
+
],
|
| 403 |
+
"logging_steps": 50,
|
| 404 |
+
"max_steps": 6000,
|
| 405 |
+
"num_input_tokens_seen": 0,
|
| 406 |
+
"num_train_epochs": 3,
|
| 407 |
+
"save_steps": 500,
|
| 408 |
+
"stateful_callbacks": {
|
| 409 |
+
"TrainerControl": {
|
| 410 |
+
"args": {
|
| 411 |
+
"should_epoch_stop": false,
|
| 412 |
+
"should_evaluate": false,
|
| 413 |
+
"should_log": false,
|
| 414 |
+
"should_save": true,
|
| 415 |
+
"should_training_stop": false
|
| 416 |
+
},
|
| 417 |
+
"attributes": {}
|
| 418 |
+
}
|
| 419 |
+
},
|
| 420 |
+
"total_flos": 1814674216845312.0,
|
| 421 |
+
"train_batch_size": 128,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee7da759e58ad315e9aab0bd0a67aaf65d967502be17f1c7422afebdd2d3e30
|
| 3 |
+
size 5393
|
checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_final_layer_norm": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 16384,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 384,
|
| 12 |
+
"decoder_attention_heads": 6,
|
| 13 |
+
"decoder_ffn_dim": 768,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 1,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"dtype": "float32",
|
| 19 |
+
"encoder_attention_heads": 6,
|
| 20 |
+
"encoder_ffn_dim": 768,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 1,
|
| 24 |
+
"forced_eos_token_id": 1,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "LABEL_0",
|
| 27 |
+
"1": "LABEL_1",
|
| 28 |
+
"2": "LABEL_2"
|
| 29 |
+
},
|
| 30 |
+
"init_std": 0.02,
|
| 31 |
+
"is_decoder": false,
|
| 32 |
+
"is_encoder_decoder": true,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1,
|
| 36 |
+
"LABEL_2": 2
|
| 37 |
+
},
|
| 38 |
+
"max_position_embeddings": 128,
|
| 39 |
+
"model_type": "bart",
|
| 40 |
+
"normalize_before": true,
|
| 41 |
+
"pad_token_id": 2,
|
| 42 |
+
"scale_embedding": true,
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "5.9.0",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 16385
|
| 47 |
+
}
|
checkpoint-3000/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 16384,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 2,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e17c31b18987ebfb7a883526dbceeb1446514808d7b81c3e0d332d76a99c6c73
|
| 3 |
+
size 96704732
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7099c0377846bd3cea23eba0ee1afadd00cdb490d013243054297449ef14adaa
|
| 3 |
+
size 193440203
|
checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3307dfed089ac6d0fa7793da1d2affc306d25135bbf2f131129ededc4300e3
|
| 3 |
+
size 14645
|
checkpoint-3000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
|
| 3 |
+
size 1383
|