Upload 10 files
Browse files- .gitattributes +1 -0
- config.json +32 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +531 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloom-560m",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"layer_norm_epsilon": 1e-05,
|
| 16 |
+
"masked_softmax_fusion": true,
|
| 17 |
+
"model_type": "bloom",
|
| 18 |
+
"n_head": 16,
|
| 19 |
+
"n_inner": null,
|
| 20 |
+
"n_layer": 24,
|
| 21 |
+
"offset_alibi": 100,
|
| 22 |
+
"pad_token_id": 3,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"skip_bias_add": true,
|
| 25 |
+
"skip_bias_add_qkv": false,
|
| 26 |
+
"slow_but_exact": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.26.1",
|
| 29 |
+
"unk_token_id": 0,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250880
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 3,
|
| 6 |
+
"transformers_version": "4.26.1"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:456a752b361d90a09d3cd7836762963970c57eac2be77a9fb3e70e7c6ac92ed0
|
| 3 |
+
size 2236957537
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81d6b47129952371ab2fd8446c1e2725d81d6a761188904442cf49d1ae386ab7
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93656d9e0614f072aed266dc2de3b65db11a6671c90e4d0fd0acac29a6389d08
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eb48f6fdbb7dd90e79cd3d6546a309dca70abd5334aaf54966470fa24ccbaa5
|
| 3 |
+
size 14500707
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "bigscience/bloom-560m",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"padding_side": "left",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"tokenizer_class": "BloomTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,531 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 37560,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 2.2617,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 4.932541824069077e-05,
|
| 19 |
+
"loss": 1.6381,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 4.865083648138155e-05,
|
| 25 |
+
"loss": 1.4975,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 4.7976254722072315e-05,
|
| 31 |
+
"loss": 1.4772,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.33,
|
| 36 |
+
"learning_rate": 4.730167296276309e-05,
|
| 37 |
+
"loss": 1.4015,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4,
|
| 42 |
+
"learning_rate": 4.662709120345386e-05,
|
| 43 |
+
"loss": 1.3626,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"learning_rate": 4.595250944414463e-05,
|
| 49 |
+
"loss": 1.3631,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.53,
|
| 54 |
+
"learning_rate": 4.5277927684835404e-05,
|
| 55 |
+
"loss": 1.3027,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.6,
|
| 60 |
+
"learning_rate": 4.460334592552617e-05,
|
| 61 |
+
"loss": 1.2998,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.67,
|
| 66 |
+
"learning_rate": 4.392876416621695e-05,
|
| 67 |
+
"loss": 1.2911,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.73,
|
| 72 |
+
"learning_rate": 4.325418240690772e-05,
|
| 73 |
+
"loss": 1.2764,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.8,
|
| 78 |
+
"learning_rate": 4.2579600647598486e-05,
|
| 79 |
+
"loss": 1.2656,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.87,
|
| 84 |
+
"learning_rate": 4.190501888828926e-05,
|
| 85 |
+
"loss": 1.2599,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.93,
|
| 90 |
+
"learning_rate": 4.123043712898003e-05,
|
| 91 |
+
"loss": 1.2488,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.0,
|
| 96 |
+
"learning_rate": 4.055585536967081e-05,
|
| 97 |
+
"loss": 1.2533,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.0,
|
| 102 |
+
"eval_bleu1_score": 0.9978,
|
| 103 |
+
"eval_bleu2_score": 0.9978,
|
| 104 |
+
"eval_bleu3_score": 0.9978,
|
| 105 |
+
"eval_bleu4_score": 0.9978,
|
| 106 |
+
"eval_loss": 1.2135246992111206,
|
| 107 |
+
"eval_rougeL": 0.9976,
|
| 108 |
+
"eval_runtime": 348.2564,
|
| 109 |
+
"eval_samples_per_second": 4.795,
|
| 110 |
+
"eval_steps_per_second": 2.398,
|
| 111 |
+
"step": 7512
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.06,
|
| 115 |
+
"learning_rate": 3.988127361036158e-05,
|
| 116 |
+
"loss": 1.0527,
|
| 117 |
+
"step": 8000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.13,
|
| 121 |
+
"learning_rate": 3.920669185105235e-05,
|
| 122 |
+
"loss": 1.0452,
|
| 123 |
+
"step": 8500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2,
|
| 127 |
+
"learning_rate": 3.8532110091743125e-05,
|
| 128 |
+
"loss": 1.0486,
|
| 129 |
+
"step": 9000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.26,
|
| 133 |
+
"learning_rate": 3.7857528332433894e-05,
|
| 134 |
+
"loss": 1.0376,
|
| 135 |
+
"step": 9500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.33,
|
| 139 |
+
"learning_rate": 3.718294657312467e-05,
|
| 140 |
+
"loss": 1.05,
|
| 141 |
+
"step": 10000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.4,
|
| 145 |
+
"learning_rate": 3.650836481381544e-05,
|
| 146 |
+
"loss": 1.0601,
|
| 147 |
+
"step": 10500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.46,
|
| 151 |
+
"learning_rate": 3.583378305450621e-05,
|
| 152 |
+
"loss": 1.0451,
|
| 153 |
+
"step": 11000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.53,
|
| 157 |
+
"learning_rate": 3.515920129519698e-05,
|
| 158 |
+
"loss": 1.0377,
|
| 159 |
+
"step": 11500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.6,
|
| 163 |
+
"learning_rate": 3.448461953588775e-05,
|
| 164 |
+
"loss": 1.0407,
|
| 165 |
+
"step": 12000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.66,
|
| 169 |
+
"learning_rate": 3.3810037776578527e-05,
|
| 170 |
+
"loss": 1.0325,
|
| 171 |
+
"step": 12500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.73,
|
| 175 |
+
"learning_rate": 3.3135456017269295e-05,
|
| 176 |
+
"loss": 1.0092,
|
| 177 |
+
"step": 13000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.8,
|
| 181 |
+
"learning_rate": 3.2460874257960064e-05,
|
| 182 |
+
"loss": 1.049,
|
| 183 |
+
"step": 13500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.86,
|
| 187 |
+
"learning_rate": 3.178629249865084e-05,
|
| 188 |
+
"loss": 1.0264,
|
| 189 |
+
"step": 14000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.93,
|
| 193 |
+
"learning_rate": 3.111171073934161e-05,
|
| 194 |
+
"loss": 1.0011,
|
| 195 |
+
"step": 14500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.0,
|
| 199 |
+
"learning_rate": 3.043712898003238e-05,
|
| 200 |
+
"loss": 1.0329,
|
| 201 |
+
"step": 15000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.0,
|
| 205 |
+
"eval_bleu1_score": 0.9978,
|
| 206 |
+
"eval_bleu2_score": 0.9978,
|
| 207 |
+
"eval_bleu3_score": 0.9978,
|
| 208 |
+
"eval_bleu4_score": 0.9978,
|
| 209 |
+
"eval_loss": 1.1185928583145142,
|
| 210 |
+
"eval_rougeL": 0.9976,
|
| 211 |
+
"eval_runtime": 347.235,
|
| 212 |
+
"eval_samples_per_second": 4.809,
|
| 213 |
+
"eval_steps_per_second": 2.405,
|
| 214 |
+
"step": 15024
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.06,
|
| 218 |
+
"learning_rate": 2.9762547220723153e-05,
|
| 219 |
+
"loss": 0.8112,
|
| 220 |
+
"step": 15500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.13,
|
| 224 |
+
"learning_rate": 2.9087965461413925e-05,
|
| 225 |
+
"loss": 0.8095,
|
| 226 |
+
"step": 16000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.2,
|
| 230 |
+
"learning_rate": 2.8413383702104697e-05,
|
| 231 |
+
"loss": 0.8018,
|
| 232 |
+
"step": 16500
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.26,
|
| 236 |
+
"learning_rate": 2.7738801942795465e-05,
|
| 237 |
+
"loss": 0.7999,
|
| 238 |
+
"step": 17000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.33,
|
| 242 |
+
"learning_rate": 2.7064220183486238e-05,
|
| 243 |
+
"loss": 0.8078,
|
| 244 |
+
"step": 17500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.4,
|
| 248 |
+
"learning_rate": 2.638963842417701e-05,
|
| 249 |
+
"loss": 0.8053,
|
| 250 |
+
"step": 18000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.46,
|
| 254 |
+
"learning_rate": 2.5715056664867782e-05,
|
| 255 |
+
"loss": 0.8008,
|
| 256 |
+
"step": 18500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.53,
|
| 260 |
+
"learning_rate": 2.5040474905558554e-05,
|
| 261 |
+
"loss": 0.8187,
|
| 262 |
+
"step": 19000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.6,
|
| 266 |
+
"learning_rate": 2.4365893146249326e-05,
|
| 267 |
+
"loss": 0.797,
|
| 268 |
+
"step": 19500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.66,
|
| 272 |
+
"learning_rate": 2.3691311386940098e-05,
|
| 273 |
+
"loss": 0.7971,
|
| 274 |
+
"step": 20000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.73,
|
| 278 |
+
"learning_rate": 2.301672962763087e-05,
|
| 279 |
+
"loss": 0.8096,
|
| 280 |
+
"step": 20500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.8,
|
| 284 |
+
"learning_rate": 2.2342147868321642e-05,
|
| 285 |
+
"loss": 0.7909,
|
| 286 |
+
"step": 21000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.86,
|
| 290 |
+
"learning_rate": 2.1667566109012415e-05,
|
| 291 |
+
"loss": 0.7939,
|
| 292 |
+
"step": 21500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.93,
|
| 296 |
+
"learning_rate": 2.0992984349703183e-05,
|
| 297 |
+
"loss": 0.7963,
|
| 298 |
+
"step": 22000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.0,
|
| 302 |
+
"learning_rate": 2.0318402590393955e-05,
|
| 303 |
+
"loss": 0.7886,
|
| 304 |
+
"step": 22500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 3.0,
|
| 308 |
+
"eval_bleu1_score": 0.9978,
|
| 309 |
+
"eval_bleu2_score": 0.9978,
|
| 310 |
+
"eval_bleu3_score": 0.9978,
|
| 311 |
+
"eval_bleu4_score": 0.9978,
|
| 312 |
+
"eval_loss": 1.1093112230300903,
|
| 313 |
+
"eval_rougeL": 0.9976,
|
| 314 |
+
"eval_runtime": 347.4161,
|
| 315 |
+
"eval_samples_per_second": 4.807,
|
| 316 |
+
"eval_steps_per_second": 2.403,
|
| 317 |
+
"step": 22536
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.06,
|
| 321 |
+
"learning_rate": 1.9643820831084728e-05,
|
| 322 |
+
"loss": 0.576,
|
| 323 |
+
"step": 23000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.13,
|
| 327 |
+
"learning_rate": 1.89692390717755e-05,
|
| 328 |
+
"loss": 0.5781,
|
| 329 |
+
"step": 23500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.19,
|
| 333 |
+
"learning_rate": 1.8294657312466272e-05,
|
| 334 |
+
"loss": 0.5698,
|
| 335 |
+
"step": 24000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.26,
|
| 339 |
+
"learning_rate": 1.762007555315704e-05,
|
| 340 |
+
"loss": 0.5717,
|
| 341 |
+
"step": 24500
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.33,
|
| 345 |
+
"learning_rate": 1.6945493793847816e-05,
|
| 346 |
+
"loss": 0.584,
|
| 347 |
+
"step": 25000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.39,
|
| 351 |
+
"learning_rate": 1.6270912034538588e-05,
|
| 352 |
+
"loss": 0.5758,
|
| 353 |
+
"step": 25500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.46,
|
| 357 |
+
"learning_rate": 1.559633027522936e-05,
|
| 358 |
+
"loss": 0.5808,
|
| 359 |
+
"step": 26000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.53,
|
| 363 |
+
"learning_rate": 1.492174851592013e-05,
|
| 364 |
+
"loss": 0.5762,
|
| 365 |
+
"step": 26500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.59,
|
| 369 |
+
"learning_rate": 1.4247166756610903e-05,
|
| 370 |
+
"loss": 0.5701,
|
| 371 |
+
"step": 27000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.66,
|
| 375 |
+
"learning_rate": 1.3572584997301673e-05,
|
| 376 |
+
"loss": 0.58,
|
| 377 |
+
"step": 27500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.73,
|
| 381 |
+
"learning_rate": 1.2898003237992445e-05,
|
| 382 |
+
"loss": 0.5683,
|
| 383 |
+
"step": 28000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.79,
|
| 387 |
+
"learning_rate": 1.2223421478683218e-05,
|
| 388 |
+
"loss": 0.5589,
|
| 389 |
+
"step": 28500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.86,
|
| 393 |
+
"learning_rate": 1.1548839719373988e-05,
|
| 394 |
+
"loss": 0.5842,
|
| 395 |
+
"step": 29000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.93,
|
| 399 |
+
"learning_rate": 1.087425796006476e-05,
|
| 400 |
+
"loss": 0.5717,
|
| 401 |
+
"step": 29500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.99,
|
| 405 |
+
"learning_rate": 1.0199676200755532e-05,
|
| 406 |
+
"loss": 0.5618,
|
| 407 |
+
"step": 30000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.0,
|
| 411 |
+
"eval_bleu1_score": 0.9978,
|
| 412 |
+
"eval_bleu2_score": 0.9978,
|
| 413 |
+
"eval_bleu3_score": 0.9978,
|
| 414 |
+
"eval_bleu4_score": 0.9978,
|
| 415 |
+
"eval_loss": 1.2060836553573608,
|
| 416 |
+
"eval_rougeL": 0.9976,
|
| 417 |
+
"eval_runtime": 347.0486,
|
| 418 |
+
"eval_samples_per_second": 4.812,
|
| 419 |
+
"eval_steps_per_second": 2.406,
|
| 420 |
+
"step": 30048
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.06,
|
| 424 |
+
"learning_rate": 9.525094441446304e-06,
|
| 425 |
+
"loss": 0.3953,
|
| 426 |
+
"step": 30500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.13,
|
| 430 |
+
"learning_rate": 8.850512682137076e-06,
|
| 431 |
+
"loss": 0.3749,
|
| 432 |
+
"step": 31000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.19,
|
| 436 |
+
"learning_rate": 8.175930922827847e-06,
|
| 437 |
+
"loss": 0.3731,
|
| 438 |
+
"step": 31500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 4.26,
|
| 442 |
+
"learning_rate": 7.501349163518619e-06,
|
| 443 |
+
"loss": 0.3752,
|
| 444 |
+
"step": 32000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.33,
|
| 448 |
+
"learning_rate": 6.82676740420939e-06,
|
| 449 |
+
"loss": 0.3789,
|
| 450 |
+
"step": 32500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 4.39,
|
| 454 |
+
"learning_rate": 6.152185644900162e-06,
|
| 455 |
+
"loss": 0.3768,
|
| 456 |
+
"step": 33000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 4.46,
|
| 460 |
+
"learning_rate": 5.477603885590934e-06,
|
| 461 |
+
"loss": 0.3665,
|
| 462 |
+
"step": 33500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.53,
|
| 466 |
+
"learning_rate": 4.803022126281705e-06,
|
| 467 |
+
"loss": 0.3763,
|
| 468 |
+
"step": 34000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 4.59,
|
| 472 |
+
"learning_rate": 4.128440366972477e-06,
|
| 473 |
+
"loss": 0.3715,
|
| 474 |
+
"step": 34500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.66,
|
| 478 |
+
"learning_rate": 3.4538586076632488e-06,
|
| 479 |
+
"loss": 0.3763,
|
| 480 |
+
"step": 35000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.73,
|
| 484 |
+
"learning_rate": 2.7792768483540205e-06,
|
| 485 |
+
"loss": 0.3727,
|
| 486 |
+
"step": 35500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 4.79,
|
| 490 |
+
"learning_rate": 2.104695089044792e-06,
|
| 491 |
+
"loss": 0.365,
|
| 492 |
+
"step": 36000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 4.86,
|
| 496 |
+
"learning_rate": 1.4301133297355639e-06,
|
| 497 |
+
"loss": 0.3707,
|
| 498 |
+
"step": 36500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 4.93,
|
| 502 |
+
"learning_rate": 7.555315704263357e-07,
|
| 503 |
+
"loss": 0.3691,
|
| 504 |
+
"step": 37000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.99,
|
| 508 |
+
"learning_rate": 8.09498111171074e-08,
|
| 509 |
+
"loss": 0.3724,
|
| 510 |
+
"step": 37500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 5.0,
|
| 514 |
+
"eval_bleu1_score": 0.9978,
|
| 515 |
+
"eval_bleu2_score": 0.9978,
|
| 516 |
+
"eval_bleu3_score": 0.9978,
|
| 517 |
+
"eval_bleu4_score": 0.9978,
|
| 518 |
+
"eval_loss": 1.51046884059906,
|
| 519 |
+
"eval_rougeL": 0.9976,
|
| 520 |
+
"eval_runtime": 347.5328,
|
| 521 |
+
"eval_samples_per_second": 4.805,
|
| 522 |
+
"eval_steps_per_second": 2.403,
|
| 523 |
+
"step": 37560
|
| 524 |
+
}
|
| 525 |
+
],
|
| 526 |
+
"max_steps": 37560,
|
| 527 |
+
"num_train_epochs": 5,
|
| 528 |
+
"total_flos": 1.08999726956544e+17,
|
| 529 |
+
"trial_name": null,
|
| 530 |
+
"trial_params": null
|
| 531 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d4aba7819cdec30a2103e83cb9ec62adc4ba4edade725a48324ca9fcf6a0c0
|
| 3 |
+
size 3579
|