Upload folder using huggingface_hub
Browse files- checkpoint-5000/config.json +32 -0
- checkpoint-5000/generation_config.json +6 -0
- checkpoint-5000/model.safetensors +3 -0
- checkpoint-5000/optimizer.pt +3 -0
- checkpoint-5000/rng_state.pth +3 -0
- checkpoint-5000/scheduler.pt +3 -0
- checkpoint-5000/special_tokens_map.json +23 -0
- checkpoint-5000/spiece.model +3 -0
- checkpoint-5000/tokenizer.json +3 -0
- checkpoint-5000/tokenizer_config.json +41 -0
- checkpoint-5000/trainer_state.json +173 -0
- checkpoint-5000/training_args.bin +3 -0
- checkpoint-5500/config.json +32 -0
- checkpoint-5500/generation_config.json +6 -0
- checkpoint-5500/model.safetensors +3 -0
- checkpoint-5500/optimizer.pt +3 -0
- checkpoint-5500/rng_state.pth +3 -0
- checkpoint-5500/scheduler.pt +3 -0
- checkpoint-5500/special_tokens_map.json +23 -0
- checkpoint-5500/spiece.model +3 -0
- checkpoint-5500/tokenizer.json +3 -0
- checkpoint-5500/tokenizer_config.json +41 -0
- checkpoint-5500/trainer_state.json +185 -0
- checkpoint-5500/training_args.bin +3 -0
- checkpoint-6000/config.json +32 -0
- checkpoint-6000/generation_config.json +6 -0
- checkpoint-6000/model.safetensors +3 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/rng_state.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/special_tokens_map.json +23 -0
- checkpoint-6000/spiece.model +3 -0
- checkpoint-6000/tokenizer.json +3 -0
- checkpoint-6000/tokenizer_config.json +41 -0
- checkpoint-6000/trainer_state.json +204 -0
- checkpoint-6000/training_args.bin +3 -0
- generation_config.json +5 -1
checkpoint-5000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "huggingface-course/mt5-finetuned-amazon-en-es",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 8,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 8,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.41.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
checkpoint-5000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.41.2"
|
| 6 |
+
}
|
checkpoint-5000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db18d0ebb02211516f5aa82cf32b01f36fae049bcad07b767416a6491863e396
|
| 3 |
+
size 1200729512
|
checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97ead2d29f9d1e68de4337a111386e3dc58a93e92cb540f028d65fff2ebb8783
|
| 3 |
+
size 2879866
|
checkpoint-5000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7f4d58b37e5548e4c4c86278d1b79aeccd7f51a8699348b00972091853eaa6d
|
| 3 |
+
size 14244
|
checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbfcf346ffa321c1893d921e3994abb0018919e4e051735a9c02d5a32adaf3ba
|
| 3 |
+
size 1064
|
checkpoint-5000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-5000/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
checkpoint-5000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ee660ae764cd56ecac9dbe82d766502034efac119fc579414afcd68d4f6b922
|
| 3 |
+
size 16315191
|
checkpoint-5000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"max_length": 30,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"stride": 0,
|
| 37 |
+
"tokenizer_class": "T5Tokenizer",
|
| 38 |
+
"truncation_side": "right",
|
| 39 |
+
"truncation_strategy": "longest_first",
|
| 40 |
+
"unk_token": "<unk>"
|
| 41 |
+
}
|
checkpoint-5000/trainer_state.json
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 75,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 1.6603230237960815,
|
| 14 |
+
"learning_rate": 0.00020833333333333335,
|
| 15 |
+
"loss": 2.7781,
|
| 16 |
+
"step": 625
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 1.839109182357788,
|
| 21 |
+
"eval_rouge1": 28.5024,
|
| 22 |
+
"eval_rouge2": 11.2717,
|
| 23 |
+
"eval_rougeL": 22.108,
|
| 24 |
+
"eval_rougeLsum": 22.4361,
|
| 25 |
+
"eval_runtime": 722.0927,
|
| 26 |
+
"eval_samples_per_second": 13.849,
|
| 27 |
+
"eval_steps_per_second": 0.866,
|
| 28 |
+
"step": 625
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 1.18350088596344,
|
| 33 |
+
"learning_rate": 0.0004166666666666667,
|
| 34 |
+
"loss": 2.0622,
|
| 35 |
+
"step": 1250
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_loss": 1.7575578689575195,
|
| 40 |
+
"eval_rouge1": 28.0245,
|
| 41 |
+
"eval_rouge2": 10.6112,
|
| 42 |
+
"eval_rougeL": 21.7353,
|
| 43 |
+
"eval_rougeLsum": 22.0685,
|
| 44 |
+
"eval_runtime": 728.2015,
|
| 45 |
+
"eval_samples_per_second": 13.732,
|
| 46 |
+
"eval_steps_per_second": 0.858,
|
| 47 |
+
"step": 1250
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 0.9635187983512878,
|
| 52 |
+
"learning_rate": 0.000625,
|
| 53 |
+
"loss": 1.8636,
|
| 54 |
+
"step": 1875
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_loss": 1.617906928062439,
|
| 59 |
+
"eval_rouge1": 27.353,
|
| 60 |
+
"eval_rouge2": 10.6238,
|
| 61 |
+
"eval_rougeL": 21.4686,
|
| 62 |
+
"eval_rougeLsum": 21.7512,
|
| 63 |
+
"eval_runtime": 730.8407,
|
| 64 |
+
"eval_samples_per_second": 13.683,
|
| 65 |
+
"eval_steps_per_second": 0.855,
|
| 66 |
+
"step": 1875
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.1745034456253052,
|
| 71 |
+
"learning_rate": 0.0008333333333333334,
|
| 72 |
+
"loss": 1.7408,
|
| 73 |
+
"step": 2500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_loss": 1.6142878532409668,
|
| 78 |
+
"eval_rouge1": 28.0928,
|
| 79 |
+
"eval_rouge2": 11.2857,
|
| 80 |
+
"eval_rougeL": 22.06,
|
| 81 |
+
"eval_rougeLsum": 22.3629,
|
| 82 |
+
"eval_runtime": 802.3401,
|
| 83 |
+
"eval_samples_per_second": 12.464,
|
| 84 |
+
"eval_steps_per_second": 0.779,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.7837355136871338,
|
| 90 |
+
"learning_rate": 0.0009615384615384616,
|
| 91 |
+
"loss": 1.6492,
|
| 92 |
+
"step": 3125
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_loss": 1.5411357879638672,
|
| 97 |
+
"eval_rouge1": 27.8209,
|
| 98 |
+
"eval_rouge2": 10.9184,
|
| 99 |
+
"eval_rougeL": 21.6819,
|
| 100 |
+
"eval_rougeLsum": 21.9773,
|
| 101 |
+
"eval_runtime": 711.0964,
|
| 102 |
+
"eval_samples_per_second": 14.063,
|
| 103 |
+
"eval_steps_per_second": 0.879,
|
| 104 |
+
"step": 3125
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 0.5993546843528748,
|
| 109 |
+
"learning_rate": 0.0007692307692307693,
|
| 110 |
+
"loss": 1.5448,
|
| 111 |
+
"step": 3750
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_loss": 1.4802035093307495,
|
| 116 |
+
"eval_rouge1": 28.0433,
|
| 117 |
+
"eval_rouge2": 11.4232,
|
| 118 |
+
"eval_rougeL": 22.0696,
|
| 119 |
+
"eval_rougeLsum": 22.373,
|
| 120 |
+
"eval_runtime": 728.4308,
|
| 121 |
+
"eval_samples_per_second": 13.728,
|
| 122 |
+
"eval_steps_per_second": 0.858,
|
| 123 |
+
"step": 3750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 0.7141011357307434,
|
| 128 |
+
"learning_rate": 0.0005769230769230769,
|
| 129 |
+
"loss": 1.4454,
|
| 130 |
+
"step": 4375
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_loss": 1.462142825126648,
|
| 135 |
+
"eval_rouge1": 27.8552,
|
| 136 |
+
"eval_rouge2": 11.1708,
|
| 137 |
+
"eval_rougeL": 21.8958,
|
| 138 |
+
"eval_rougeLsum": 22.1949,
|
| 139 |
+
"eval_runtime": 640.7723,
|
| 140 |
+
"eval_samples_per_second": 15.606,
|
| 141 |
+
"eval_steps_per_second": 0.975,
|
| 142 |
+
"step": 4375
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.6400988101959229,
|
| 147 |
+
"learning_rate": 0.00038461538461538467,
|
| 148 |
+
"loss": 1.3636,
|
| 149 |
+
"step": 5000
|
| 150 |
+
}
|
| 151 |
+
],
|
| 152 |
+
"logging_steps": 625,
|
| 153 |
+
"max_steps": 6250,
|
| 154 |
+
"num_input_tokens_seen": 0,
|
| 155 |
+
"num_train_epochs": 10,
|
| 156 |
+
"save_steps": 500,
|
| 157 |
+
"stateful_callbacks": {
|
| 158 |
+
"TrainerControl": {
|
| 159 |
+
"args": {
|
| 160 |
+
"should_epoch_stop": false,
|
| 161 |
+
"should_evaluate": false,
|
| 162 |
+
"should_log": false,
|
| 163 |
+
"should_save": true,
|
| 164 |
+
"should_training_stop": false
|
| 165 |
+
},
|
| 166 |
+
"attributes": {}
|
| 167 |
+
}
|
| 168 |
+
},
|
| 169 |
+
"total_flos": 4.22999752704e+16,
|
| 170 |
+
"train_batch_size": 16,
|
| 171 |
+
"trial_name": null,
|
| 172 |
+
"trial_params": null
|
| 173 |
+
}
|
checkpoint-5000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f5223adea68bac22d3e503304376f99d2113ed58ad54d362e129fa184482b15
|
| 3 |
+
size 5240
|
checkpoint-5500/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "huggingface-course/mt5-finetuned-amazon-en-es",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 8,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 8,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.41.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
checkpoint-5500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.41.2"
|
| 6 |
+
}
|
checkpoint-5500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7544a75019487033c3697fe99b3d493fc268f49f4f76ff1509cb98a95895c400
|
| 3 |
+
size 1200729512
|
checkpoint-5500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92780dc81daec4c9e2c8e024f806a36df6e3d35eec087590f361167876766d95
|
| 3 |
+
size 2879866
|
checkpoint-5500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eacade89a99076612b2685c06f1897e40328f5d9e642936aed8178e83d63949b
|
| 3 |
+
size 14244
|
checkpoint-5500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09e85770e7a5d92bd875c851b84e34b820f78c9d6ff7a152f8bd524e42bd0243
|
| 3 |
+
size 1064
|
checkpoint-5500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-5500/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
checkpoint-5500/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ee660ae764cd56ecac9dbe82d766502034efac119fc579414afcd68d4f6b922
|
| 3 |
+
size 16315191
|
checkpoint-5500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"max_length": 30,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"stride": 0,
|
| 37 |
+
"tokenizer_class": "T5Tokenizer",
|
| 38 |
+
"truncation_side": "right",
|
| 39 |
+
"truncation_strategy": "longest_first",
|
| 40 |
+
"unk_token": "<unk>"
|
| 41 |
+
}
|
checkpoint-5500/trainer_state.json
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.8,
|
| 5 |
+
"eval_steps": 75,
|
| 6 |
+
"global_step": 5500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 1.6603230237960815,
|
| 14 |
+
"learning_rate": 0.00020833333333333335,
|
| 15 |
+
"loss": 2.7781,
|
| 16 |
+
"step": 625
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 1.839109182357788,
|
| 21 |
+
"eval_rouge1": 28.5024,
|
| 22 |
+
"eval_rouge2": 11.2717,
|
| 23 |
+
"eval_rougeL": 22.108,
|
| 24 |
+
"eval_rougeLsum": 22.4361,
|
| 25 |
+
"eval_runtime": 722.0927,
|
| 26 |
+
"eval_samples_per_second": 13.849,
|
| 27 |
+
"eval_steps_per_second": 0.866,
|
| 28 |
+
"step": 625
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 1.18350088596344,
|
| 33 |
+
"learning_rate": 0.0004166666666666667,
|
| 34 |
+
"loss": 2.0622,
|
| 35 |
+
"step": 1250
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_loss": 1.7575578689575195,
|
| 40 |
+
"eval_rouge1": 28.0245,
|
| 41 |
+
"eval_rouge2": 10.6112,
|
| 42 |
+
"eval_rougeL": 21.7353,
|
| 43 |
+
"eval_rougeLsum": 22.0685,
|
| 44 |
+
"eval_runtime": 728.2015,
|
| 45 |
+
"eval_samples_per_second": 13.732,
|
| 46 |
+
"eval_steps_per_second": 0.858,
|
| 47 |
+
"step": 1250
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 0.9635187983512878,
|
| 52 |
+
"learning_rate": 0.000625,
|
| 53 |
+
"loss": 1.8636,
|
| 54 |
+
"step": 1875
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_loss": 1.617906928062439,
|
| 59 |
+
"eval_rouge1": 27.353,
|
| 60 |
+
"eval_rouge2": 10.6238,
|
| 61 |
+
"eval_rougeL": 21.4686,
|
| 62 |
+
"eval_rougeLsum": 21.7512,
|
| 63 |
+
"eval_runtime": 730.8407,
|
| 64 |
+
"eval_samples_per_second": 13.683,
|
| 65 |
+
"eval_steps_per_second": 0.855,
|
| 66 |
+
"step": 1875
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.1745034456253052,
|
| 71 |
+
"learning_rate": 0.0008333333333333334,
|
| 72 |
+
"loss": 1.7408,
|
| 73 |
+
"step": 2500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_loss": 1.6142878532409668,
|
| 78 |
+
"eval_rouge1": 28.0928,
|
| 79 |
+
"eval_rouge2": 11.2857,
|
| 80 |
+
"eval_rougeL": 22.06,
|
| 81 |
+
"eval_rougeLsum": 22.3629,
|
| 82 |
+
"eval_runtime": 802.3401,
|
| 83 |
+
"eval_samples_per_second": 12.464,
|
| 84 |
+
"eval_steps_per_second": 0.779,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.7837355136871338,
|
| 90 |
+
"learning_rate": 0.0009615384615384616,
|
| 91 |
+
"loss": 1.6492,
|
| 92 |
+
"step": 3125
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_loss": 1.5411357879638672,
|
| 97 |
+
"eval_rouge1": 27.8209,
|
| 98 |
+
"eval_rouge2": 10.9184,
|
| 99 |
+
"eval_rougeL": 21.6819,
|
| 100 |
+
"eval_rougeLsum": 21.9773,
|
| 101 |
+
"eval_runtime": 711.0964,
|
| 102 |
+
"eval_samples_per_second": 14.063,
|
| 103 |
+
"eval_steps_per_second": 0.879,
|
| 104 |
+
"step": 3125
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 0.5993546843528748,
|
| 109 |
+
"learning_rate": 0.0007692307692307693,
|
| 110 |
+
"loss": 1.5448,
|
| 111 |
+
"step": 3750
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_loss": 1.4802035093307495,
|
| 116 |
+
"eval_rouge1": 28.0433,
|
| 117 |
+
"eval_rouge2": 11.4232,
|
| 118 |
+
"eval_rougeL": 22.0696,
|
| 119 |
+
"eval_rougeLsum": 22.373,
|
| 120 |
+
"eval_runtime": 728.4308,
|
| 121 |
+
"eval_samples_per_second": 13.728,
|
| 122 |
+
"eval_steps_per_second": 0.858,
|
| 123 |
+
"step": 3750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 0.7141011357307434,
|
| 128 |
+
"learning_rate": 0.0005769230769230769,
|
| 129 |
+
"loss": 1.4454,
|
| 130 |
+
"step": 4375
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_loss": 1.462142825126648,
|
| 135 |
+
"eval_rouge1": 27.8552,
|
| 136 |
+
"eval_rouge2": 11.1708,
|
| 137 |
+
"eval_rougeL": 21.8958,
|
| 138 |
+
"eval_rougeLsum": 22.1949,
|
| 139 |
+
"eval_runtime": 640.7723,
|
| 140 |
+
"eval_samples_per_second": 15.606,
|
| 141 |
+
"eval_steps_per_second": 0.975,
|
| 142 |
+
"step": 4375
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.6400988101959229,
|
| 147 |
+
"learning_rate": 0.00038461538461538467,
|
| 148 |
+
"loss": 1.3636,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 1.4522408246994019,
|
| 154 |
+
"eval_rouge1": 28.3264,
|
| 155 |
+
"eval_rouge2": 11.7945,
|
| 156 |
+
"eval_rougeL": 22.3563,
|
| 157 |
+
"eval_rougeLsum": 22.6524,
|
| 158 |
+
"eval_runtime": 715.9922,
|
| 159 |
+
"eval_samples_per_second": 13.967,
|
| 160 |
+
"eval_steps_per_second": 0.873,
|
| 161 |
+
"step": 5000
|
| 162 |
+
}
|
| 163 |
+
],
|
| 164 |
+
"logging_steps": 625,
|
| 165 |
+
"max_steps": 6250,
|
| 166 |
+
"num_input_tokens_seen": 0,
|
| 167 |
+
"num_train_epochs": 10,
|
| 168 |
+
"save_steps": 500,
|
| 169 |
+
"stateful_callbacks": {
|
| 170 |
+
"TrainerControl": {
|
| 171 |
+
"args": {
|
| 172 |
+
"should_epoch_stop": false,
|
| 173 |
+
"should_evaluate": false,
|
| 174 |
+
"should_log": false,
|
| 175 |
+
"should_save": true,
|
| 176 |
+
"should_training_stop": false
|
| 177 |
+
},
|
| 178 |
+
"attributes": {}
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"total_flos": 4.652997279744e+16,
|
| 182 |
+
"train_batch_size": 16,
|
| 183 |
+
"trial_name": null,
|
| 184 |
+
"trial_params": null
|
| 185 |
+
}
|
checkpoint-5500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f5223adea68bac22d3e503304376f99d2113ed58ad54d362e129fa184482b15
|
| 3 |
+
size 5240
|
checkpoint-6000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "huggingface-course/mt5-finetuned-amazon-en-es",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 8,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 8,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.41.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
checkpoint-6000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.41.2"
|
| 6 |
+
}
|
checkpoint-6000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89f623f4a01b722905510276a1a06b7b68cd255827e342e4c3ca4ddee56ed498
|
| 3 |
+
size 1200729512
|
checkpoint-6000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a089a3a25c69d2de6113cea9c64a35519129aaf471e2172dfc6e07e6723a273b
|
| 3 |
+
size 2879866
|
checkpoint-6000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:656e79bc514cbc36d830d5dd590d52aac19362cdb25a3184fb8a1d03468f9a60
|
| 3 |
+
size 14244
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:608dba54e3cf2298f5418707e0dd61313fe32d937145e62ea0bb8a1f2fd326d8
|
| 3 |
+
size 1064
|
checkpoint-6000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-6000/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
checkpoint-6000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ee660ae764cd56ecac9dbe82d766502034efac119fc579414afcd68d4f6b922
|
| 3 |
+
size 16315191
|
checkpoint-6000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"max_length": 30,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"stride": 0,
|
| 37 |
+
"tokenizer_class": "T5Tokenizer",
|
| 38 |
+
"truncation_side": "right",
|
| 39 |
+
"truncation_strategy": "longest_first",
|
| 40 |
+
"unk_token": "<unk>"
|
| 41 |
+
}
|
checkpoint-6000/trainer_state.json
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.6,
|
| 5 |
+
"eval_steps": 75,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 1.6603230237960815,
|
| 14 |
+
"learning_rate": 0.00020833333333333335,
|
| 15 |
+
"loss": 2.7781,
|
| 16 |
+
"step": 625
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 1.839109182357788,
|
| 21 |
+
"eval_rouge1": 28.5024,
|
| 22 |
+
"eval_rouge2": 11.2717,
|
| 23 |
+
"eval_rougeL": 22.108,
|
| 24 |
+
"eval_rougeLsum": 22.4361,
|
| 25 |
+
"eval_runtime": 722.0927,
|
| 26 |
+
"eval_samples_per_second": 13.849,
|
| 27 |
+
"eval_steps_per_second": 0.866,
|
| 28 |
+
"step": 625
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 1.18350088596344,
|
| 33 |
+
"learning_rate": 0.0004166666666666667,
|
| 34 |
+
"loss": 2.0622,
|
| 35 |
+
"step": 1250
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_loss": 1.7575578689575195,
|
| 40 |
+
"eval_rouge1": 28.0245,
|
| 41 |
+
"eval_rouge2": 10.6112,
|
| 42 |
+
"eval_rougeL": 21.7353,
|
| 43 |
+
"eval_rougeLsum": 22.0685,
|
| 44 |
+
"eval_runtime": 728.2015,
|
| 45 |
+
"eval_samples_per_second": 13.732,
|
| 46 |
+
"eval_steps_per_second": 0.858,
|
| 47 |
+
"step": 1250
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 0.9635187983512878,
|
| 52 |
+
"learning_rate": 0.000625,
|
| 53 |
+
"loss": 1.8636,
|
| 54 |
+
"step": 1875
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_loss": 1.617906928062439,
|
| 59 |
+
"eval_rouge1": 27.353,
|
| 60 |
+
"eval_rouge2": 10.6238,
|
| 61 |
+
"eval_rougeL": 21.4686,
|
| 62 |
+
"eval_rougeLsum": 21.7512,
|
| 63 |
+
"eval_runtime": 730.8407,
|
| 64 |
+
"eval_samples_per_second": 13.683,
|
| 65 |
+
"eval_steps_per_second": 0.855,
|
| 66 |
+
"step": 1875
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.1745034456253052,
|
| 71 |
+
"learning_rate": 0.0008333333333333334,
|
| 72 |
+
"loss": 1.7408,
|
| 73 |
+
"step": 2500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_loss": 1.6142878532409668,
|
| 78 |
+
"eval_rouge1": 28.0928,
|
| 79 |
+
"eval_rouge2": 11.2857,
|
| 80 |
+
"eval_rougeL": 22.06,
|
| 81 |
+
"eval_rougeLsum": 22.3629,
|
| 82 |
+
"eval_runtime": 802.3401,
|
| 83 |
+
"eval_samples_per_second": 12.464,
|
| 84 |
+
"eval_steps_per_second": 0.779,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.7837355136871338,
|
| 90 |
+
"learning_rate": 0.0009615384615384616,
|
| 91 |
+
"loss": 1.6492,
|
| 92 |
+
"step": 3125
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_loss": 1.5411357879638672,
|
| 97 |
+
"eval_rouge1": 27.8209,
|
| 98 |
+
"eval_rouge2": 10.9184,
|
| 99 |
+
"eval_rougeL": 21.6819,
|
| 100 |
+
"eval_rougeLsum": 21.9773,
|
| 101 |
+
"eval_runtime": 711.0964,
|
| 102 |
+
"eval_samples_per_second": 14.063,
|
| 103 |
+
"eval_steps_per_second": 0.879,
|
| 104 |
+
"step": 3125
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 0.5993546843528748,
|
| 109 |
+
"learning_rate": 0.0007692307692307693,
|
| 110 |
+
"loss": 1.5448,
|
| 111 |
+
"step": 3750
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_loss": 1.4802035093307495,
|
| 116 |
+
"eval_rouge1": 28.0433,
|
| 117 |
+
"eval_rouge2": 11.4232,
|
| 118 |
+
"eval_rougeL": 22.0696,
|
| 119 |
+
"eval_rougeLsum": 22.373,
|
| 120 |
+
"eval_runtime": 728.4308,
|
| 121 |
+
"eval_samples_per_second": 13.728,
|
| 122 |
+
"eval_steps_per_second": 0.858,
|
| 123 |
+
"step": 3750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 0.7141011357307434,
|
| 128 |
+
"learning_rate": 0.0005769230769230769,
|
| 129 |
+
"loss": 1.4454,
|
| 130 |
+
"step": 4375
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_loss": 1.462142825126648,
|
| 135 |
+
"eval_rouge1": 27.8552,
|
| 136 |
+
"eval_rouge2": 11.1708,
|
| 137 |
+
"eval_rougeL": 21.8958,
|
| 138 |
+
"eval_rougeLsum": 22.1949,
|
| 139 |
+
"eval_runtime": 640.7723,
|
| 140 |
+
"eval_samples_per_second": 15.606,
|
| 141 |
+
"eval_steps_per_second": 0.975,
|
| 142 |
+
"step": 4375
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.6400988101959229,
|
| 147 |
+
"learning_rate": 0.00038461538461538467,
|
| 148 |
+
"loss": 1.3636,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 1.4522408246994019,
|
| 154 |
+
"eval_rouge1": 28.3264,
|
| 155 |
+
"eval_rouge2": 11.7945,
|
| 156 |
+
"eval_rougeL": 22.3563,
|
| 157 |
+
"eval_rougeLsum": 22.6524,
|
| 158 |
+
"eval_runtime": 715.9922,
|
| 159 |
+
"eval_samples_per_second": 13.967,
|
| 160 |
+
"eval_steps_per_second": 0.873,
|
| 161 |
+
"step": 5000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 0.6958301067352295,
|
| 166 |
+
"learning_rate": 0.00019230769230769233,
|
| 167 |
+
"loss": 1.2978,
|
| 168 |
+
"step": 5625
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_loss": 1.4346853494644165,
|
| 173 |
+
"eval_rouge1": 28.444,
|
| 174 |
+
"eval_rouge2": 11.9388,
|
| 175 |
+
"eval_rougeL": 22.4279,
|
| 176 |
+
"eval_rougeLsum": 22.7344,
|
| 177 |
+
"eval_runtime": 652.829,
|
| 178 |
+
"eval_samples_per_second": 15.318,
|
| 179 |
+
"eval_steps_per_second": 0.957,
|
| 180 |
+
"step": 5625
|
| 181 |
+
}
|
| 182 |
+
],
|
| 183 |
+
"logging_steps": 625,
|
| 184 |
+
"max_steps": 6250,
|
| 185 |
+
"num_input_tokens_seen": 0,
|
| 186 |
+
"num_train_epochs": 10,
|
| 187 |
+
"save_steps": 500,
|
| 188 |
+
"stateful_callbacks": {
|
| 189 |
+
"TrainerControl": {
|
| 190 |
+
"args": {
|
| 191 |
+
"should_epoch_stop": false,
|
| 192 |
+
"should_evaluate": false,
|
| 193 |
+
"should_log": false,
|
| 194 |
+
"should_save": true,
|
| 195 |
+
"should_training_stop": false
|
| 196 |
+
},
|
| 197 |
+
"attributes": {}
|
| 198 |
+
}
|
| 199 |
+
},
|
| 200 |
+
"total_flos": 5.075997032448e+16,
|
| 201 |
+
"train_batch_size": 16,
|
| 202 |
+
"trial_name": null,
|
| 203 |
+
"trial_params": null
|
| 204 |
+
}
|
checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f5223adea68bac22d3e503304376f99d2113ed58ad54d362e129fa184482b15
|
| 3 |
+
size 5240
|
generation_config.json
CHANGED
|
@@ -2,5 +2,9 @@
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
| 5 |
-
"transformers_version": "4.41.2"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.41.2",
|
| 6 |
+
"max_length": 256,
|
| 7 |
+
"num_beams": 5,
|
| 8 |
+
"no_repeat_ngram_size": 2,
|
| 9 |
+
"early_stopping": 1
|
| 10 |
}
|