Add model files
Browse files- config.json +75 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +776 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.10.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:026a3fddcfd1fc7501d87992c85c6a38ea3b2bc46f774780e085377e7dd7f4d1
|
| 3 |
+
size 1115525925
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2be7a986f9c8b40c2bc11ac6cda37b66365895aa6520b40b6588cb2c765c0f0
|
| 3 |
+
size 557985683
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49cc2126dd94cd21c86c2fc21ab29e989e36b330124f1f31aa02df8517db1df3
|
| 3 |
+
size 14657
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c247c24e0064024789544f370000d8f892d145c9ee5590d20a357a0bb99ab62a
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,776 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9042719006538391,
|
| 3 |
+
"best_model_checkpoint": "/gscratch/xlab/hallisky/rewriting/src/models/toxic/bart-base_2.5e-05_0_32_jigsaw_randmask/checkpoint-38000",
|
| 4 |
+
"epoch": 10.552624271035823,
|
| 5 |
+
"global_step": 38000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 2.4750000000000002e-05,
|
| 13 |
+
"loss": 1.2139,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.28,
|
| 18 |
+
"learning_rate": 2.45e-05,
|
| 19 |
+
"loss": 1.1274,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.28,
|
| 24 |
+
"eval_loss": 0.9955187439918518,
|
| 25 |
+
"eval_runtime": 183.7737,
|
| 26 |
+
"eval_samples_per_second": 158.445,
|
| 27 |
+
"eval_steps_per_second": 1.241,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.42,
|
| 32 |
+
"learning_rate": 2.425e-05,
|
| 33 |
+
"loss": 1.1115,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.56,
|
| 38 |
+
"learning_rate": 2.4e-05,
|
| 39 |
+
"loss": 1.0866,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.56,
|
| 44 |
+
"eval_loss": 0.9784897565841675,
|
| 45 |
+
"eval_runtime": 183.1935,
|
| 46 |
+
"eval_samples_per_second": 158.947,
|
| 47 |
+
"eval_steps_per_second": 1.245,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.69,
|
| 52 |
+
"learning_rate": 2.375e-05,
|
| 53 |
+
"loss": 1.0865,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.83,
|
| 58 |
+
"learning_rate": 2.35e-05,
|
| 59 |
+
"loss": 1.0748,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.83,
|
| 64 |
+
"eval_loss": 0.9661561846733093,
|
| 65 |
+
"eval_runtime": 183.3031,
|
| 66 |
+
"eval_samples_per_second": 158.852,
|
| 67 |
+
"eval_steps_per_second": 1.244,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.97,
|
| 72 |
+
"learning_rate": 2.3250000000000003e-05,
|
| 73 |
+
"loss": 1.073,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.11,
|
| 78 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 79 |
+
"loss": 1.0481,
|
| 80 |
+
"step": 4000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.11,
|
| 84 |
+
"eval_loss": 0.9609841704368591,
|
| 85 |
+
"eval_runtime": 183.0018,
|
| 86 |
+
"eval_samples_per_second": 159.113,
|
| 87 |
+
"eval_steps_per_second": 1.246,
|
| 88 |
+
"step": 4000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.25,
|
| 92 |
+
"learning_rate": 2.275e-05,
|
| 93 |
+
"loss": 1.0424,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.39,
|
| 98 |
+
"learning_rate": 2.25e-05,
|
| 99 |
+
"loss": 1.0441,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.39,
|
| 104 |
+
"eval_loss": 0.9524271488189697,
|
| 105 |
+
"eval_runtime": 183.0159,
|
| 106 |
+
"eval_samples_per_second": 159.101,
|
| 107 |
+
"eval_steps_per_second": 1.246,
|
| 108 |
+
"step": 5000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.53,
|
| 112 |
+
"learning_rate": 2.2250000000000002e-05,
|
| 113 |
+
"loss": 1.0383,
|
| 114 |
+
"step": 5500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.67,
|
| 118 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 119 |
+
"loss": 1.0368,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.67,
|
| 124 |
+
"eval_loss": 0.9480794668197632,
|
| 125 |
+
"eval_runtime": 183.0254,
|
| 126 |
+
"eval_samples_per_second": 159.093,
|
| 127 |
+
"eval_steps_per_second": 1.246,
|
| 128 |
+
"step": 6000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.81,
|
| 132 |
+
"learning_rate": 2.175e-05,
|
| 133 |
+
"loss": 1.0295,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.94,
|
| 138 |
+
"learning_rate": 2.15e-05,
|
| 139 |
+
"loss": 1.0294,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.94,
|
| 144 |
+
"eval_loss": 0.9428065419197083,
|
| 145 |
+
"eval_runtime": 183.0141,
|
| 146 |
+
"eval_samples_per_second": 159.103,
|
| 147 |
+
"eval_steps_per_second": 1.246,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.08,
|
| 152 |
+
"learning_rate": 2.125e-05,
|
| 153 |
+
"loss": 1.0213,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.22,
|
| 158 |
+
"learning_rate": 2.1e-05,
|
| 159 |
+
"loss": 1.0148,
|
| 160 |
+
"step": 8000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.22,
|
| 164 |
+
"eval_loss": 0.9450138807296753,
|
| 165 |
+
"eval_runtime": 182.9272,
|
| 166 |
+
"eval_samples_per_second": 159.178,
|
| 167 |
+
"eval_steps_per_second": 1.246,
|
| 168 |
+
"step": 8000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.36,
|
| 172 |
+
"learning_rate": 2.075e-05,
|
| 173 |
+
"loss": 1.0141,
|
| 174 |
+
"step": 8500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.5,
|
| 178 |
+
"learning_rate": 2.05e-05,
|
| 179 |
+
"loss": 1.0136,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.5,
|
| 184 |
+
"eval_loss": 0.9394757151603699,
|
| 185 |
+
"eval_runtime": 183.1908,
|
| 186 |
+
"eval_samples_per_second": 158.949,
|
| 187 |
+
"eval_steps_per_second": 1.245,
|
| 188 |
+
"step": 9000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.64,
|
| 192 |
+
"learning_rate": 2.025e-05,
|
| 193 |
+
"loss": 1.0117,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.78,
|
| 198 |
+
"learning_rate": 2e-05,
|
| 199 |
+
"loss": 1.0083,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.78,
|
| 204 |
+
"eval_loss": 0.9403573274612427,
|
| 205 |
+
"eval_runtime": 182.9098,
|
| 206 |
+
"eval_samples_per_second": 159.193,
|
| 207 |
+
"eval_steps_per_second": 1.247,
|
| 208 |
+
"step": 10000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.92,
|
| 212 |
+
"learning_rate": 1.9750000000000002e-05,
|
| 213 |
+
"loss": 1.0062,
|
| 214 |
+
"step": 10500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.05,
|
| 218 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 219 |
+
"loss": 1.0045,
|
| 220 |
+
"step": 11000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.05,
|
| 224 |
+
"eval_loss": 0.9311016201972961,
|
| 225 |
+
"eval_runtime": 182.9614,
|
| 226 |
+
"eval_samples_per_second": 159.148,
|
| 227 |
+
"eval_steps_per_second": 1.246,
|
| 228 |
+
"step": 11000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.19,
|
| 232 |
+
"learning_rate": 1.925e-05,
|
| 233 |
+
"loss": 0.9962,
|
| 234 |
+
"step": 11500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.33,
|
| 238 |
+
"learning_rate": 1.9e-05,
|
| 239 |
+
"loss": 0.9913,
|
| 240 |
+
"step": 12000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.33,
|
| 244 |
+
"eval_loss": 0.9348850846290588,
|
| 245 |
+
"eval_runtime": 182.9469,
|
| 246 |
+
"eval_samples_per_second": 159.161,
|
| 247 |
+
"eval_steps_per_second": 1.246,
|
| 248 |
+
"step": 12000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.47,
|
| 252 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 253 |
+
"loss": 0.9914,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.61,
|
| 258 |
+
"learning_rate": 1.85e-05,
|
| 259 |
+
"loss": 0.9925,
|
| 260 |
+
"step": 13000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.61,
|
| 264 |
+
"eval_loss": 0.9286701679229736,
|
| 265 |
+
"eval_runtime": 182.7432,
|
| 266 |
+
"eval_samples_per_second": 159.338,
|
| 267 |
+
"eval_steps_per_second": 1.248,
|
| 268 |
+
"step": 13000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.75,
|
| 272 |
+
"learning_rate": 1.825e-05,
|
| 273 |
+
"loss": 0.9957,
|
| 274 |
+
"step": 13500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.89,
|
| 278 |
+
"learning_rate": 1.8e-05,
|
| 279 |
+
"loss": 0.9929,
|
| 280 |
+
"step": 14000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.89,
|
| 284 |
+
"eval_loss": 0.9286787509918213,
|
| 285 |
+
"eval_runtime": 183.092,
|
| 286 |
+
"eval_samples_per_second": 159.035,
|
| 287 |
+
"eval_steps_per_second": 1.245,
|
| 288 |
+
"step": 14000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.03,
|
| 292 |
+
"learning_rate": 1.775e-05,
|
| 293 |
+
"loss": 0.9873,
|
| 294 |
+
"step": 14500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.17,
|
| 298 |
+
"learning_rate": 1.75e-05,
|
| 299 |
+
"loss": 0.9825,
|
| 300 |
+
"step": 15000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 4.17,
|
| 304 |
+
"eval_loss": 0.9284389615058899,
|
| 305 |
+
"eval_runtime": 183.0692,
|
| 306 |
+
"eval_samples_per_second": 159.055,
|
| 307 |
+
"eval_steps_per_second": 1.245,
|
| 308 |
+
"step": 15000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.3,
|
| 312 |
+
"learning_rate": 1.725e-05,
|
| 313 |
+
"loss": 0.9791,
|
| 314 |
+
"step": 15500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.44,
|
| 318 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 319 |
+
"loss": 0.9761,
|
| 320 |
+
"step": 16000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.44,
|
| 324 |
+
"eval_loss": 0.9231427311897278,
|
| 325 |
+
"eval_runtime": 182.9694,
|
| 326 |
+
"eval_samples_per_second": 159.141,
|
| 327 |
+
"eval_steps_per_second": 1.246,
|
| 328 |
+
"step": 16000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.58,
|
| 332 |
+
"learning_rate": 1.675e-05,
|
| 333 |
+
"loss": 0.9806,
|
| 334 |
+
"step": 16500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.72,
|
| 338 |
+
"learning_rate": 1.65e-05,
|
| 339 |
+
"loss": 0.9788,
|
| 340 |
+
"step": 17000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.72,
|
| 344 |
+
"eval_loss": 0.9270732998847961,
|
| 345 |
+
"eval_runtime": 182.9924,
|
| 346 |
+
"eval_samples_per_second": 159.121,
|
| 347 |
+
"eval_steps_per_second": 1.246,
|
| 348 |
+
"step": 17000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4.86,
|
| 352 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 353 |
+
"loss": 0.9771,
|
| 354 |
+
"step": 17500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 5.0,
|
| 358 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 359 |
+
"loss": 0.9799,
|
| 360 |
+
"step": 18000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 5.0,
|
| 364 |
+
"eval_loss": 0.9208848476409912,
|
| 365 |
+
"eval_runtime": 183.0859,
|
| 366 |
+
"eval_samples_per_second": 159.04,
|
| 367 |
+
"eval_steps_per_second": 1.245,
|
| 368 |
+
"step": 18000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.14,
|
| 372 |
+
"learning_rate": 1.575e-05,
|
| 373 |
+
"loss": 0.9684,
|
| 374 |
+
"step": 18500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.28,
|
| 378 |
+
"learning_rate": 1.55e-05,
|
| 379 |
+
"loss": 0.9655,
|
| 380 |
+
"step": 19000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.28,
|
| 384 |
+
"eval_loss": 0.9188591837882996,
|
| 385 |
+
"eval_runtime": 183.2317,
|
| 386 |
+
"eval_samples_per_second": 158.914,
|
| 387 |
+
"eval_steps_per_second": 1.244,
|
| 388 |
+
"step": 19000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.42,
|
| 392 |
+
"learning_rate": 1.525e-05,
|
| 393 |
+
"loss": 0.969,
|
| 394 |
+
"step": 19500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.55,
|
| 398 |
+
"learning_rate": 1.5e-05,
|
| 399 |
+
"loss": 0.9678,
|
| 400 |
+
"step": 20000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 5.55,
|
| 404 |
+
"eval_loss": 0.920549213886261,
|
| 405 |
+
"eval_runtime": 182.9534,
|
| 406 |
+
"eval_samples_per_second": 159.155,
|
| 407 |
+
"eval_steps_per_second": 1.246,
|
| 408 |
+
"step": 20000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.69,
|
| 412 |
+
"learning_rate": 1.475e-05,
|
| 413 |
+
"loss": 0.9672,
|
| 414 |
+
"step": 20500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.83,
|
| 418 |
+
"learning_rate": 1.45e-05,
|
| 419 |
+
"loss": 0.9723,
|
| 420 |
+
"step": 21000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.83,
|
| 424 |
+
"eval_loss": 0.9192747473716736,
|
| 425 |
+
"eval_runtime": 182.9328,
|
| 426 |
+
"eval_samples_per_second": 159.173,
|
| 427 |
+
"eval_steps_per_second": 1.246,
|
| 428 |
+
"step": 21000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.97,
|
| 432 |
+
"learning_rate": 1.4249999999999999e-05,
|
| 433 |
+
"loss": 0.9667,
|
| 434 |
+
"step": 21500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.11,
|
| 438 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 439 |
+
"loss": 0.9603,
|
| 440 |
+
"step": 22000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.11,
|
| 444 |
+
"eval_loss": 0.9202588200569153,
|
| 445 |
+
"eval_runtime": 182.9947,
|
| 446 |
+
"eval_samples_per_second": 159.119,
|
| 447 |
+
"eval_steps_per_second": 1.246,
|
| 448 |
+
"step": 22000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 6.25,
|
| 452 |
+
"learning_rate": 1.3750000000000002e-05,
|
| 453 |
+
"loss": 0.9589,
|
| 454 |
+
"step": 22500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 6.39,
|
| 458 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 459 |
+
"loss": 0.9593,
|
| 460 |
+
"step": 23000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 6.39,
|
| 464 |
+
"eval_loss": 0.9192423820495605,
|
| 465 |
+
"eval_runtime": 183.1637,
|
| 466 |
+
"eval_samples_per_second": 158.973,
|
| 467 |
+
"eval_steps_per_second": 1.245,
|
| 468 |
+
"step": 23000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 6.53,
|
| 472 |
+
"learning_rate": 1.3250000000000002e-05,
|
| 473 |
+
"loss": 0.961,
|
| 474 |
+
"step": 23500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 6.66,
|
| 478 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 479 |
+
"loss": 0.9634,
|
| 480 |
+
"step": 24000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 6.66,
|
| 484 |
+
"eval_loss": 0.9148619771003723,
|
| 485 |
+
"eval_runtime": 182.8693,
|
| 486 |
+
"eval_samples_per_second": 159.228,
|
| 487 |
+
"eval_steps_per_second": 1.247,
|
| 488 |
+
"step": 24000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.8,
|
| 492 |
+
"learning_rate": 1.2750000000000002e-05,
|
| 493 |
+
"loss": 0.958,
|
| 494 |
+
"step": 24500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.94,
|
| 498 |
+
"learning_rate": 1.25e-05,
|
| 499 |
+
"loss": 0.9577,
|
| 500 |
+
"step": 25000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.94,
|
| 504 |
+
"eval_loss": 0.9157229065895081,
|
| 505 |
+
"eval_runtime": 182.8974,
|
| 506 |
+
"eval_samples_per_second": 159.204,
|
| 507 |
+
"eval_steps_per_second": 1.247,
|
| 508 |
+
"step": 25000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 7.08,
|
| 512 |
+
"learning_rate": 1.225e-05,
|
| 513 |
+
"loss": 0.9543,
|
| 514 |
+
"step": 25500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 7.22,
|
| 518 |
+
"learning_rate": 1.2e-05,
|
| 519 |
+
"loss": 0.9505,
|
| 520 |
+
"step": 26000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.22,
|
| 524 |
+
"eval_loss": 0.9146404266357422,
|
| 525 |
+
"eval_runtime": 182.7838,
|
| 526 |
+
"eval_samples_per_second": 159.303,
|
| 527 |
+
"eval_steps_per_second": 1.247,
|
| 528 |
+
"step": 26000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 7.36,
|
| 532 |
+
"learning_rate": 1.175e-05,
|
| 533 |
+
"loss": 0.9478,
|
| 534 |
+
"step": 26500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.5,
|
| 538 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 539 |
+
"loss": 0.9546,
|
| 540 |
+
"step": 27000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 7.5,
|
| 544 |
+
"eval_loss": 0.9135451912879944,
|
| 545 |
+
"eval_runtime": 182.7429,
|
| 546 |
+
"eval_samples_per_second": 159.339,
|
| 547 |
+
"eval_steps_per_second": 1.248,
|
| 548 |
+
"step": 27000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.64,
|
| 552 |
+
"learning_rate": 1.125e-05,
|
| 553 |
+
"loss": 0.9481,
|
| 554 |
+
"step": 27500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 7.78,
|
| 558 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 559 |
+
"loss": 0.948,
|
| 560 |
+
"step": 28000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 7.78,
|
| 564 |
+
"eval_loss": 0.9123603701591492,
|
| 565 |
+
"eval_runtime": 183.1278,
|
| 566 |
+
"eval_samples_per_second": 159.004,
|
| 567 |
+
"eval_steps_per_second": 1.245,
|
| 568 |
+
"step": 28000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 7.91,
|
| 572 |
+
"learning_rate": 1.075e-05,
|
| 573 |
+
"loss": 0.948,
|
| 574 |
+
"step": 28500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 8.05,
|
| 578 |
+
"learning_rate": 1.05e-05,
|
| 579 |
+
"loss": 0.9461,
|
| 580 |
+
"step": 29000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 8.05,
|
| 584 |
+
"eval_loss": 0.9139257073402405,
|
| 585 |
+
"eval_runtime": 182.9341,
|
| 586 |
+
"eval_samples_per_second": 159.172,
|
| 587 |
+
"eval_steps_per_second": 1.246,
|
| 588 |
+
"step": 29000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 8.19,
|
| 592 |
+
"learning_rate": 1.025e-05,
|
| 593 |
+
"loss": 0.9442,
|
| 594 |
+
"step": 29500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 8.33,
|
| 598 |
+
"learning_rate": 1e-05,
|
| 599 |
+
"loss": 0.9441,
|
| 600 |
+
"step": 30000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 8.33,
|
| 604 |
+
"eval_loss": 0.9109994173049927,
|
| 605 |
+
"eval_runtime": 451.1148,
|
| 606 |
+
"eval_samples_per_second": 64.547,
|
| 607 |
+
"eval_steps_per_second": 0.505,
|
| 608 |
+
"step": 30000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 8.47,
|
| 612 |
+
"learning_rate": 9.750000000000002e-06,
|
| 613 |
+
"loss": 0.9431,
|
| 614 |
+
"step": 30500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 8.61,
|
| 618 |
+
"learning_rate": 9.5e-06,
|
| 619 |
+
"loss": 0.9408,
|
| 620 |
+
"step": 31000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 8.61,
|
| 624 |
+
"eval_loss": 0.911307692527771,
|
| 625 |
+
"eval_runtime": 182.7894,
|
| 626 |
+
"eval_samples_per_second": 159.298,
|
| 627 |
+
"eval_steps_per_second": 1.247,
|
| 628 |
+
"step": 31000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 8.75,
|
| 632 |
+
"learning_rate": 9.25e-06,
|
| 633 |
+
"loss": 0.9429,
|
| 634 |
+
"step": 31500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 8.89,
|
| 638 |
+
"learning_rate": 9e-06,
|
| 639 |
+
"loss": 0.9391,
|
| 640 |
+
"step": 32000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 8.89,
|
| 644 |
+
"eval_loss": 0.9080024361610413,
|
| 645 |
+
"eval_runtime": 183.033,
|
| 646 |
+
"eval_samples_per_second": 159.086,
|
| 647 |
+
"eval_steps_per_second": 1.246,
|
| 648 |
+
"step": 32000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 9.03,
|
| 652 |
+
"learning_rate": 8.75e-06,
|
| 653 |
+
"loss": 0.9427,
|
| 654 |
+
"step": 32500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 9.16,
|
| 658 |
+
"learning_rate": 8.500000000000002e-06,
|
| 659 |
+
"loss": 0.942,
|
| 660 |
+
"step": 33000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.16,
|
| 664 |
+
"eval_loss": 0.909125804901123,
|
| 665 |
+
"eval_runtime": 183.0287,
|
| 666 |
+
"eval_samples_per_second": 159.09,
|
| 667 |
+
"eval_steps_per_second": 1.246,
|
| 668 |
+
"step": 33000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 9.3,
|
| 672 |
+
"learning_rate": 8.25e-06,
|
| 673 |
+
"loss": 0.9371,
|
| 674 |
+
"step": 33500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.44,
|
| 678 |
+
"learning_rate": 8.000000000000001e-06,
|
| 679 |
+
"loss": 0.9338,
|
| 680 |
+
"step": 34000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 9.44,
|
| 684 |
+
"eval_loss": 0.9082431793212891,
|
| 685 |
+
"eval_runtime": 183.1001,
|
| 686 |
+
"eval_samples_per_second": 159.028,
|
| 687 |
+
"eval_steps_per_second": 1.245,
|
| 688 |
+
"step": 34000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 9.58,
|
| 692 |
+
"learning_rate": 7.75e-06,
|
| 693 |
+
"loss": 0.9354,
|
| 694 |
+
"step": 34500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 9.72,
|
| 698 |
+
"learning_rate": 7.5e-06,
|
| 699 |
+
"loss": 0.9337,
|
| 700 |
+
"step": 35000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 9.72,
|
| 704 |
+
"eval_loss": 0.9084173440933228,
|
| 705 |
+
"eval_runtime": 183.0616,
|
| 706 |
+
"eval_samples_per_second": 159.061,
|
| 707 |
+
"eval_steps_per_second": 1.245,
|
| 708 |
+
"step": 35000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 9.86,
|
| 712 |
+
"learning_rate": 7.25e-06,
|
| 713 |
+
"loss": 0.9358,
|
| 714 |
+
"step": 35500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 10.0,
|
| 718 |
+
"learning_rate": 7.000000000000001e-06,
|
| 719 |
+
"loss": 0.9355,
|
| 720 |
+
"step": 36000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 10.0,
|
| 724 |
+
"eval_loss": 0.907382071018219,
|
| 725 |
+
"eval_runtime": 183.0579,
|
| 726 |
+
"eval_samples_per_second": 159.064,
|
| 727 |
+
"eval_steps_per_second": 1.246,
|
| 728 |
+
"step": 36000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 10.14,
|
| 732 |
+
"learning_rate": 6.750000000000001e-06,
|
| 733 |
+
"loss": 0.9324,
|
| 734 |
+
"step": 36500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 10.27,
|
| 738 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 739 |
+
"loss": 0.9323,
|
| 740 |
+
"step": 37000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 10.27,
|
| 744 |
+
"eval_loss": 0.9063876271247864,
|
| 745 |
+
"eval_runtime": 183.0015,
|
| 746 |
+
"eval_samples_per_second": 159.113,
|
| 747 |
+
"eval_steps_per_second": 1.246,
|
| 748 |
+
"step": 37000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 10.41,
|
| 752 |
+
"learning_rate": 6.25e-06,
|
| 753 |
+
"loss": 0.9295,
|
| 754 |
+
"step": 37500
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 10.55,
|
| 758 |
+
"learning_rate": 6e-06,
|
| 759 |
+
"loss": 0.9321,
|
| 760 |
+
"step": 38000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 10.55,
|
| 764 |
+
"eval_loss": 0.9042719006538391,
|
| 765 |
+
"eval_runtime": 183.0185,
|
| 766 |
+
"eval_samples_per_second": 159.099,
|
| 767 |
+
"eval_steps_per_second": 1.246,
|
| 768 |
+
"step": 38000
|
| 769 |
+
}
|
| 770 |
+
],
|
| 771 |
+
"max_steps": 50000,
|
| 772 |
+
"num_train_epochs": 14,
|
| 773 |
+
"total_flos": 1.4479335456768e+17,
|
| 774 |
+
"trial_name": null,
|
| 775 |
+
"trial_params": null
|
| 776 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bf9a0be625181016629c54aaf2999eee3a84334de71ff8ffd3eee321be326f8
|
| 3 |
+
size 2735
|