Upload folder using huggingface_hub
Browse files- config.json +25 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +948 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/l/users/muhammad.dehan/repository/TokenAlignmentMulti/models/models/mbert-3-5e-5/checkpoint-112000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.47.0",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.47.0"
|
| 5 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35fec0fe89e40d29f9fd28d3025d4209748c80176ad26541773fe582e02b0750
|
| 3 |
+
size 438080896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3c3452e7d6e7095be0768632b6f67cb9c2dd33f132abaf275a052f26435f3e4
|
| 3 |
+
size 876283258
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60cf99305f2ec4d93009d5ce13a49718e903289880368ce5b981933985749494
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1ebf6c7ff920096b20c37ac0095094a16c11f1f6b095e2a4cf1cc53ab192016
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6703945398330688,
|
| 3 |
+
"best_model_checkpoint": "models/models/mbert-3-5e-5/checkpoint-116000",
|
| 4 |
+
"epoch": 49.998677383253636,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 122850,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8139179977617255,
|
| 13 |
+
"grad_norm": 9.055466651916504,
|
| 14 |
+
"learning_rate": 4.796499796499796e-05,
|
| 15 |
+
"loss": 5.8944,
|
| 16 |
+
"step": 2000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8139179977617255,
|
| 20 |
+
"eval_loss": 5.142313480377197,
|
| 21 |
+
"eval_runtime": 73.0566,
|
| 22 |
+
"eval_samples_per_second": 136.88,
|
| 23 |
+
"eval_steps_per_second": 2.149,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.6275307762742903,
|
| 28 |
+
"grad_norm": 14.413078308105469,
|
| 29 |
+
"learning_rate": 4.592999592999594e-05,
|
| 30 |
+
"loss": 4.8554,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.6275307762742903,
|
| 35 |
+
"eval_loss": 4.169687747955322,
|
| 36 |
+
"eval_runtime": 73.0805,
|
| 37 |
+
"eval_samples_per_second": 136.835,
|
| 38 |
+
"eval_steps_per_second": 2.148,
|
| 39 |
+
"step": 4000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.4411435547868554,
|
| 43 |
+
"grad_norm": 10.98070240020752,
|
| 44 |
+
"learning_rate": 4.38949938949939e-05,
|
| 45 |
+
"loss": 3.8936,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.4411435547868554,
|
| 50 |
+
"eval_loss": 3.520249605178833,
|
| 51 |
+
"eval_runtime": 73.0468,
|
| 52 |
+
"eval_samples_per_second": 136.898,
|
| 53 |
+
"eval_steps_per_second": 2.149,
|
| 54 |
+
"step": 6000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.25475633329942,
|
| 58 |
+
"grad_norm": 12.734247207641602,
|
| 59 |
+
"learning_rate": 4.185999185999186e-05,
|
| 60 |
+
"loss": 3.3719,
|
| 61 |
+
"step": 8000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 3.25475633329942,
|
| 65 |
+
"eval_loss": 3.012561082839966,
|
| 66 |
+
"eval_runtime": 73.0351,
|
| 67 |
+
"eval_samples_per_second": 136.92,
|
| 68 |
+
"eval_steps_per_second": 2.15,
|
| 69 |
+
"step": 8000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.068369111811985,
|
| 73 |
+
"grad_norm": 11.761553764343262,
|
| 74 |
+
"learning_rate": 3.9824989824989825e-05,
|
| 75 |
+
"loss": 2.9884,
|
| 76 |
+
"step": 10000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.068369111811985,
|
| 80 |
+
"eval_loss": 2.7652907371520996,
|
| 81 |
+
"eval_runtime": 73.0559,
|
| 82 |
+
"eval_samples_per_second": 136.882,
|
| 83 |
+
"eval_steps_per_second": 2.149,
|
| 84 |
+
"step": 10000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.882287109573711,
|
| 88 |
+
"grad_norm": 12.824328422546387,
|
| 89 |
+
"learning_rate": 3.778998778998779e-05,
|
| 90 |
+
"loss": 2.7846,
|
| 91 |
+
"step": 12000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 4.882287109573711,
|
| 95 |
+
"eval_loss": 2.616189956665039,
|
| 96 |
+
"eval_runtime": 73.0493,
|
| 97 |
+
"eval_samples_per_second": 136.894,
|
| 98 |
+
"eval_steps_per_second": 2.149,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 5.6958998880862755,
|
| 103 |
+
"grad_norm": 12.507063865661621,
|
| 104 |
+
"learning_rate": 3.575498575498576e-05,
|
| 105 |
+
"loss": 2.6443,
|
| 106 |
+
"step": 14000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 5.6958998880862755,
|
| 110 |
+
"eval_loss": 2.491734504699707,
|
| 111 |
+
"eval_runtime": 73.0626,
|
| 112 |
+
"eval_samples_per_second": 136.869,
|
| 113 |
+
"eval_steps_per_second": 2.149,
|
| 114 |
+
"step": 14000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 6.50951266659884,
|
| 118 |
+
"grad_norm": 12.569066047668457,
|
| 119 |
+
"learning_rate": 3.371998371998372e-05,
|
| 120 |
+
"loss": 2.5361,
|
| 121 |
+
"step": 16000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 6.50951266659884,
|
| 125 |
+
"eval_loss": 2.402878522872925,
|
| 126 |
+
"eval_runtime": 73.0516,
|
| 127 |
+
"eval_samples_per_second": 136.89,
|
| 128 |
+
"eval_steps_per_second": 2.149,
|
| 129 |
+
"step": 16000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.323125445111405,
|
| 133 |
+
"grad_norm": 12.419079780578613,
|
| 134 |
+
"learning_rate": 3.168498168498169e-05,
|
| 135 |
+
"loss": 2.4558,
|
| 136 |
+
"step": 18000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.323125445111405,
|
| 140 |
+
"eval_loss": 2.3287837505340576,
|
| 141 |
+
"eval_runtime": 73.0774,
|
| 142 |
+
"eval_samples_per_second": 136.841,
|
| 143 |
+
"eval_steps_per_second": 2.148,
|
| 144 |
+
"step": 18000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.13673822362397,
|
| 148 |
+
"grad_norm": 12.206134796142578,
|
| 149 |
+
"learning_rate": 2.9649979649979655e-05,
|
| 150 |
+
"loss": 2.3847,
|
| 151 |
+
"step": 20000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.13673822362397,
|
| 155 |
+
"eval_loss": 2.2792084217071533,
|
| 156 |
+
"eval_runtime": 73.059,
|
| 157 |
+
"eval_samples_per_second": 136.876,
|
| 158 |
+
"eval_steps_per_second": 2.149,
|
| 159 |
+
"step": 20000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.950656221385696,
|
| 163 |
+
"grad_norm": 12.273974418640137,
|
| 164 |
+
"learning_rate": 2.7614977614977615e-05,
|
| 165 |
+
"loss": 2.3293,
|
| 166 |
+
"step": 22000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 8.950656221385696,
|
| 170 |
+
"eval_loss": 2.2214159965515137,
|
| 171 |
+
"eval_runtime": 73.07,
|
| 172 |
+
"eval_samples_per_second": 136.855,
|
| 173 |
+
"eval_steps_per_second": 2.149,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.76426899989826,
|
| 178 |
+
"grad_norm": 12.672439575195312,
|
| 179 |
+
"learning_rate": 2.557997557997558e-05,
|
| 180 |
+
"loss": 2.2763,
|
| 181 |
+
"step": 24000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 9.76426899989826,
|
| 185 |
+
"eval_loss": 2.1826987266540527,
|
| 186 |
+
"eval_runtime": 73.0461,
|
| 187 |
+
"eval_samples_per_second": 136.9,
|
| 188 |
+
"eval_steps_per_second": 2.149,
|
| 189 |
+
"step": 24000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.577881778410825,
|
| 193 |
+
"grad_norm": 12.514191627502441,
|
| 194 |
+
"learning_rate": 2.3544973544973546e-05,
|
| 195 |
+
"loss": 2.2361,
|
| 196 |
+
"step": 26000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.577881778410825,
|
| 200 |
+
"eval_loss": 2.1435160636901855,
|
| 201 |
+
"eval_runtime": 73.0345,
|
| 202 |
+
"eval_samples_per_second": 136.922,
|
| 203 |
+
"eval_steps_per_second": 2.15,
|
| 204 |
+
"step": 26000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 11.39149455692339,
|
| 208 |
+
"grad_norm": 12.286685943603516,
|
| 209 |
+
"learning_rate": 2.150997150997151e-05,
|
| 210 |
+
"loss": 2.1973,
|
| 211 |
+
"step": 28000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 11.39149455692339,
|
| 215 |
+
"eval_loss": 2.1050431728363037,
|
| 216 |
+
"eval_runtime": 73.0521,
|
| 217 |
+
"eval_samples_per_second": 136.889,
|
| 218 |
+
"eval_steps_per_second": 2.149,
|
| 219 |
+
"step": 28000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.209990843422526,
|
| 223 |
+
"grad_norm": 12.680660247802734,
|
| 224 |
+
"learning_rate": 2.9649979649979655e-05,
|
| 225 |
+
"loss": 2.1805,
|
| 226 |
+
"step": 30000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 12.209990843422526,
|
| 230 |
+
"eval_loss": 2.0837137699127197,
|
| 231 |
+
"eval_runtime": 73.1666,
|
| 232 |
+
"eval_samples_per_second": 136.674,
|
| 233 |
+
"eval_steps_per_second": 2.146,
|
| 234 |
+
"step": 30000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 13.02360362193509,
|
| 238 |
+
"grad_norm": 12.36361026763916,
|
| 239 |
+
"learning_rate": 2.8293311626644965e-05,
|
| 240 |
+
"loss": 2.1418,
|
| 241 |
+
"step": 32000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 13.02360362193509,
|
| 245 |
+
"eval_loss": 2.052241802215576,
|
| 246 |
+
"eval_runtime": 73.1973,
|
| 247 |
+
"eval_samples_per_second": 136.617,
|
| 248 |
+
"eval_steps_per_second": 2.145,
|
| 249 |
+
"step": 32000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.837521619696815,
|
| 253 |
+
"grad_norm": 12.344305992126465,
|
| 254 |
+
"learning_rate": 2.693664360331027e-05,
|
| 255 |
+
"loss": 2.1107,
|
| 256 |
+
"step": 34000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.837521619696815,
|
| 260 |
+
"eval_loss": 2.0308263301849365,
|
| 261 |
+
"eval_runtime": 73.2003,
|
| 262 |
+
"eval_samples_per_second": 136.611,
|
| 263 |
+
"eval_steps_per_second": 2.145,
|
| 264 |
+
"step": 34000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 14.651134398209381,
|
| 268 |
+
"grad_norm": 12.52969741821289,
|
| 269 |
+
"learning_rate": 2.557997557997558e-05,
|
| 270 |
+
"loss": 2.0818,
|
| 271 |
+
"step": 36000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 14.651134398209381,
|
| 275 |
+
"eval_loss": 2.0151000022888184,
|
| 276 |
+
"eval_runtime": 73.21,
|
| 277 |
+
"eval_samples_per_second": 136.593,
|
| 278 |
+
"eval_steps_per_second": 2.145,
|
| 279 |
+
"step": 36000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 15.464747176721945,
|
| 283 |
+
"grad_norm": 12.168683052062988,
|
| 284 |
+
"learning_rate": 2.4223307556640893e-05,
|
| 285 |
+
"loss": 2.0559,
|
| 286 |
+
"step": 38000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 15.464747176721945,
|
| 290 |
+
"eval_loss": 1.9706333875656128,
|
| 291 |
+
"eval_runtime": 73.1868,
|
| 292 |
+
"eval_samples_per_second": 136.637,
|
| 293 |
+
"eval_steps_per_second": 2.145,
|
| 294 |
+
"step": 38000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.27835995523451,
|
| 298 |
+
"grad_norm": 12.408997535705566,
|
| 299 |
+
"learning_rate": 2.28666395333062e-05,
|
| 300 |
+
"loss": 2.0272,
|
| 301 |
+
"step": 40000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.27835995523451,
|
| 305 |
+
"eval_loss": 1.9658160209655762,
|
| 306 |
+
"eval_runtime": 73.2254,
|
| 307 |
+
"eval_samples_per_second": 136.565,
|
| 308 |
+
"eval_steps_per_second": 2.144,
|
| 309 |
+
"step": 40000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 17.091972733747074,
|
| 313 |
+
"grad_norm": 13.222212791442871,
|
| 314 |
+
"learning_rate": 2.150997150997151e-05,
|
| 315 |
+
"loss": 2.0069,
|
| 316 |
+
"step": 42000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 17.091972733747074,
|
| 320 |
+
"eval_loss": 1.9462146759033203,
|
| 321 |
+
"eval_runtime": 73.2046,
|
| 322 |
+
"eval_samples_per_second": 136.603,
|
| 323 |
+
"eval_steps_per_second": 2.145,
|
| 324 |
+
"step": 42000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.9058907315088,
|
| 328 |
+
"grad_norm": 12.432639122009277,
|
| 329 |
+
"learning_rate": 2.015330348663682e-05,
|
| 330 |
+
"loss": 1.9873,
|
| 331 |
+
"step": 44000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 17.9058907315088,
|
| 335 |
+
"eval_loss": 1.9287099838256836,
|
| 336 |
+
"eval_runtime": 73.196,
|
| 337 |
+
"eval_samples_per_second": 136.619,
|
| 338 |
+
"eval_steps_per_second": 2.145,
|
| 339 |
+
"step": 44000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.719503510021365,
|
| 343 |
+
"grad_norm": 12.828729629516602,
|
| 344 |
+
"learning_rate": 1.879663546330213e-05,
|
| 345 |
+
"loss": 1.9696,
|
| 346 |
+
"step": 46000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 18.719503510021365,
|
| 350 |
+
"eval_loss": 1.9102226495742798,
|
| 351 |
+
"eval_runtime": 73.1921,
|
| 352 |
+
"eval_samples_per_second": 136.627,
|
| 353 |
+
"eval_steps_per_second": 2.145,
|
| 354 |
+
"step": 46000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 19.53311628853393,
|
| 358 |
+
"grad_norm": 12.529792785644531,
|
| 359 |
+
"learning_rate": 1.743996743996744e-05,
|
| 360 |
+
"loss": 1.9506,
|
| 361 |
+
"step": 48000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 19.53311628853393,
|
| 365 |
+
"eval_loss": 1.8978015184402466,
|
| 366 |
+
"eval_runtime": 73.2056,
|
| 367 |
+
"eval_samples_per_second": 136.602,
|
| 368 |
+
"eval_steps_per_second": 2.145,
|
| 369 |
+
"step": 48000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 20.346729067046496,
|
| 373 |
+
"grad_norm": 12.476061820983887,
|
| 374 |
+
"learning_rate": 1.6083299416632748e-05,
|
| 375 |
+
"loss": 1.937,
|
| 376 |
+
"step": 50000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 20.346729067046496,
|
| 380 |
+
"eval_loss": 1.8884605169296265,
|
| 381 |
+
"eval_runtime": 73.211,
|
| 382 |
+
"eval_samples_per_second": 136.592,
|
| 383 |
+
"eval_steps_per_second": 2.144,
|
| 384 |
+
"step": 50000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 21.16034184555906,
|
| 388 |
+
"grad_norm": 12.546550750732422,
|
| 389 |
+
"learning_rate": 1.472663139329806e-05,
|
| 390 |
+
"loss": 1.9239,
|
| 391 |
+
"step": 52000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 21.16034184555906,
|
| 395 |
+
"eval_loss": 1.8613293170928955,
|
| 396 |
+
"eval_runtime": 73.2024,
|
| 397 |
+
"eval_samples_per_second": 136.608,
|
| 398 |
+
"eval_steps_per_second": 2.145,
|
| 399 |
+
"step": 52000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 21.974259843320784,
|
| 403 |
+
"grad_norm": 12.588421821594238,
|
| 404 |
+
"learning_rate": 1.336996336996337e-05,
|
| 405 |
+
"loss": 1.9106,
|
| 406 |
+
"step": 54000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 21.974259843320784,
|
| 410 |
+
"eval_loss": 1.8496237993240356,
|
| 411 |
+
"eval_runtime": 73.1844,
|
| 412 |
+
"eval_samples_per_second": 136.641,
|
| 413 |
+
"eval_steps_per_second": 2.145,
|
| 414 |
+
"step": 54000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 22.78787262183335,
|
| 418 |
+
"grad_norm": 12.508979797363281,
|
| 419 |
+
"learning_rate": 1.2013295346628681e-05,
|
| 420 |
+
"loss": 1.9004,
|
| 421 |
+
"step": 56000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 22.78787262183335,
|
| 425 |
+
"eval_loss": 1.8513011932373047,
|
| 426 |
+
"eval_runtime": 73.1881,
|
| 427 |
+
"eval_samples_per_second": 136.634,
|
| 428 |
+
"eval_steps_per_second": 2.145,
|
| 429 |
+
"step": 56000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 23.605961949333604,
|
| 433 |
+
"grad_norm": 12.510702133178711,
|
| 434 |
+
"learning_rate": 2.0492470492470494e-05,
|
| 435 |
+
"loss": 1.8995,
|
| 436 |
+
"step": 58000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 23.605961949333604,
|
| 440 |
+
"eval_loss": 1.8457722663879395,
|
| 441 |
+
"eval_runtime": 73.2143,
|
| 442 |
+
"eval_samples_per_second": 136.585,
|
| 443 |
+
"eval_steps_per_second": 2.144,
|
| 444 |
+
"step": 58000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 24.419574727846168,
|
| 448 |
+
"grad_norm": 12.43933391571045,
|
| 449 |
+
"learning_rate": 1.9474969474969477e-05,
|
| 450 |
+
"loss": 1.8903,
|
| 451 |
+
"step": 60000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 24.419574727846168,
|
| 455 |
+
"eval_loss": 1.8323436975479126,
|
| 456 |
+
"eval_runtime": 73.2612,
|
| 457 |
+
"eval_samples_per_second": 136.498,
|
| 458 |
+
"eval_steps_per_second": 2.143,
|
| 459 |
+
"step": 60000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 25.233187506358735,
|
| 463 |
+
"grad_norm": 12.256065368652344,
|
| 464 |
+
"learning_rate": 1.8457468457468458e-05,
|
| 465 |
+
"loss": 1.8754,
|
| 466 |
+
"step": 62000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 25.233187506358735,
|
| 470 |
+
"eval_loss": 1.8291531801223755,
|
| 471 |
+
"eval_runtime": 73.2439,
|
| 472 |
+
"eval_samples_per_second": 136.53,
|
| 473 |
+
"eval_steps_per_second": 2.144,
|
| 474 |
+
"step": 62000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 26.0468002848713,
|
| 478 |
+
"grad_norm": 12.613372802734375,
|
| 479 |
+
"learning_rate": 1.743996743996744e-05,
|
| 480 |
+
"loss": 1.8644,
|
| 481 |
+
"step": 64000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 26.0468002848713,
|
| 485 |
+
"eval_loss": 1.823506236076355,
|
| 486 |
+
"eval_runtime": 73.2487,
|
| 487 |
+
"eval_samples_per_second": 136.521,
|
| 488 |
+
"eval_steps_per_second": 2.143,
|
| 489 |
+
"step": 64000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 26.860718282633023,
|
| 493 |
+
"grad_norm": 12.547616958618164,
|
| 494 |
+
"learning_rate": 1.642246642246642e-05,
|
| 495 |
+
"loss": 1.8537,
|
| 496 |
+
"step": 66000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 26.860718282633023,
|
| 500 |
+
"eval_loss": 1.7943871021270752,
|
| 501 |
+
"eval_runtime": 73.2466,
|
| 502 |
+
"eval_samples_per_second": 136.525,
|
| 503 |
+
"eval_steps_per_second": 2.143,
|
| 504 |
+
"step": 66000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 27.67433106114559,
|
| 508 |
+
"grad_norm": 12.599259376525879,
|
| 509 |
+
"learning_rate": 1.5404965404965405e-05,
|
| 510 |
+
"loss": 1.8426,
|
| 511 |
+
"step": 68000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 27.67433106114559,
|
| 515 |
+
"eval_loss": 1.787021517753601,
|
| 516 |
+
"eval_runtime": 73.2491,
|
| 517 |
+
"eval_samples_per_second": 136.52,
|
| 518 |
+
"eval_steps_per_second": 2.143,
|
| 519 |
+
"step": 68000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 28.487943839658154,
|
| 523 |
+
"grad_norm": 12.874439239501953,
|
| 524 |
+
"learning_rate": 1.4387464387464389e-05,
|
| 525 |
+
"loss": 1.8307,
|
| 526 |
+
"step": 70000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 28.487943839658154,
|
| 530 |
+
"eval_loss": 1.7922056913375854,
|
| 531 |
+
"eval_runtime": 73.2621,
|
| 532 |
+
"eval_samples_per_second": 136.496,
|
| 533 |
+
"eval_steps_per_second": 2.143,
|
| 534 |
+
"step": 70000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 29.301556618170718,
|
| 538 |
+
"grad_norm": 12.278645515441895,
|
| 539 |
+
"learning_rate": 1.336996336996337e-05,
|
| 540 |
+
"loss": 1.8235,
|
| 541 |
+
"step": 72000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 29.301556618170718,
|
| 545 |
+
"eval_loss": 1.7722290754318237,
|
| 546 |
+
"eval_runtime": 73.2392,
|
| 547 |
+
"eval_samples_per_second": 136.539,
|
| 548 |
+
"eval_steps_per_second": 2.144,
|
| 549 |
+
"step": 72000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 30.115169396683285,
|
| 553 |
+
"grad_norm": 12.372228622436523,
|
| 554 |
+
"learning_rate": 1.2352462352462353e-05,
|
| 555 |
+
"loss": 1.8142,
|
| 556 |
+
"step": 74000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 30.115169396683285,
|
| 560 |
+
"eval_loss": 1.7639870643615723,
|
| 561 |
+
"eval_runtime": 73.2474,
|
| 562 |
+
"eval_samples_per_second": 136.524,
|
| 563 |
+
"eval_steps_per_second": 2.143,
|
| 564 |
+
"step": 74000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 30.92908739444501,
|
| 568 |
+
"grad_norm": 13.026344299316406,
|
| 569 |
+
"learning_rate": 1.1334961334961336e-05,
|
| 570 |
+
"loss": 1.8052,
|
| 571 |
+
"step": 76000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 30.92908739444501,
|
| 575 |
+
"eval_loss": 1.7618211507797241,
|
| 576 |
+
"eval_runtime": 73.2535,
|
| 577 |
+
"eval_samples_per_second": 136.512,
|
| 578 |
+
"eval_steps_per_second": 2.143,
|
| 579 |
+
"step": 76000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 31.742700172957573,
|
| 583 |
+
"grad_norm": 12.346455574035645,
|
| 584 |
+
"learning_rate": 1.0317460317460318e-05,
|
| 585 |
+
"loss": 1.7968,
|
| 586 |
+
"step": 78000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 31.742700172957573,
|
| 590 |
+
"eval_loss": 1.7621996402740479,
|
| 591 |
+
"eval_runtime": 73.2566,
|
| 592 |
+
"eval_samples_per_second": 136.506,
|
| 593 |
+
"eval_steps_per_second": 2.143,
|
| 594 |
+
"step": 78000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 32.55631295147014,
|
| 598 |
+
"grad_norm": 12.404403686523438,
|
| 599 |
+
"learning_rate": 9.2999592999593e-06,
|
| 600 |
+
"loss": 1.7906,
|
| 601 |
+
"step": 80000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 32.55631295147014,
|
| 605 |
+
"eval_loss": 1.7546992301940918,
|
| 606 |
+
"eval_runtime": 73.2436,
|
| 607 |
+
"eval_samples_per_second": 136.531,
|
| 608 |
+
"eval_steps_per_second": 2.144,
|
| 609 |
+
"step": 80000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 33.369925729982704,
|
| 613 |
+
"grad_norm": 13.407048225402832,
|
| 614 |
+
"learning_rate": 8.282458282458284e-06,
|
| 615 |
+
"loss": 1.7831,
|
| 616 |
+
"step": 82000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 33.369925729982704,
|
| 620 |
+
"eval_loss": 1.7637808322906494,
|
| 621 |
+
"eval_runtime": 73.252,
|
| 622 |
+
"eval_samples_per_second": 136.515,
|
| 623 |
+
"eval_steps_per_second": 2.143,
|
| 624 |
+
"step": 82000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 34.18353850849527,
|
| 628 |
+
"grad_norm": 12.677322387695312,
|
| 629 |
+
"learning_rate": 7.264957264957266e-06,
|
| 630 |
+
"loss": 1.7781,
|
| 631 |
+
"step": 84000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 34.18353850849527,
|
| 635 |
+
"eval_loss": 1.7423206567764282,
|
| 636 |
+
"eval_runtime": 73.2424,
|
| 637 |
+
"eval_samples_per_second": 136.533,
|
| 638 |
+
"eval_steps_per_second": 2.144,
|
| 639 |
+
"step": 84000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 35.0020347949944,
|
| 643 |
+
"grad_norm": 12.919666290283203,
|
| 644 |
+
"learning_rate": 1.4997964997965e-05,
|
| 645 |
+
"loss": 1.7839,
|
| 646 |
+
"step": 86000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 35.0020347949944,
|
| 650 |
+
"eval_loss": 1.7404271364212036,
|
| 651 |
+
"eval_runtime": 73.1021,
|
| 652 |
+
"eval_samples_per_second": 136.795,
|
| 653 |
+
"eval_steps_per_second": 2.148,
|
| 654 |
+
"step": 86000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 35.81595279275613,
|
| 658 |
+
"grad_norm": 13.499661445617676,
|
| 659 |
+
"learning_rate": 1.4183964183964185e-05,
|
| 660 |
+
"loss": 1.7779,
|
| 661 |
+
"step": 88000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 35.81595279275613,
|
| 665 |
+
"eval_loss": 1.7452839612960815,
|
| 666 |
+
"eval_runtime": 73.1263,
|
| 667 |
+
"eval_samples_per_second": 136.75,
|
| 668 |
+
"eval_steps_per_second": 2.147,
|
| 669 |
+
"step": 88000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 36.62956557126869,
|
| 673 |
+
"grad_norm": 12.777277946472168,
|
| 674 |
+
"learning_rate": 1.336996336996337e-05,
|
| 675 |
+
"loss": 1.7694,
|
| 676 |
+
"step": 90000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 36.62956557126869,
|
| 680 |
+
"eval_loss": 1.7361302375793457,
|
| 681 |
+
"eval_runtime": 73.1394,
|
| 682 |
+
"eval_samples_per_second": 136.725,
|
| 683 |
+
"eval_steps_per_second": 2.147,
|
| 684 |
+
"step": 90000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 37.443178349781256,
|
| 688 |
+
"grad_norm": 12.409318923950195,
|
| 689 |
+
"learning_rate": 1.2555962555962556e-05,
|
| 690 |
+
"loss": 1.7634,
|
| 691 |
+
"step": 92000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 37.443178349781256,
|
| 695 |
+
"eval_loss": 1.7353118658065796,
|
| 696 |
+
"eval_runtime": 73.1692,
|
| 697 |
+
"eval_samples_per_second": 136.669,
|
| 698 |
+
"eval_steps_per_second": 2.146,
|
| 699 |
+
"step": 92000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 38.25679112829383,
|
| 703 |
+
"grad_norm": 13.48429012298584,
|
| 704 |
+
"learning_rate": 1.1741961741961743e-05,
|
| 705 |
+
"loss": 1.7593,
|
| 706 |
+
"step": 94000
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 38.25679112829383,
|
| 710 |
+
"eval_loss": 1.7299132347106934,
|
| 711 |
+
"eval_runtime": 73.1218,
|
| 712 |
+
"eval_samples_per_second": 136.758,
|
| 713 |
+
"eval_steps_per_second": 2.147,
|
| 714 |
+
"step": 94000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 39.07040390680639,
|
| 718 |
+
"grad_norm": 12.476696014404297,
|
| 719 |
+
"learning_rate": 1.0927960927960928e-05,
|
| 720 |
+
"loss": 1.7498,
|
| 721 |
+
"step": 96000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 39.07040390680639,
|
| 725 |
+
"eval_loss": 1.7091785669326782,
|
| 726 |
+
"eval_runtime": 73.0912,
|
| 727 |
+
"eval_samples_per_second": 136.815,
|
| 728 |
+
"eval_steps_per_second": 2.148,
|
| 729 |
+
"step": 96000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 39.88432190456812,
|
| 733 |
+
"grad_norm": 13.220356941223145,
|
| 734 |
+
"learning_rate": 1.0113960113960115e-05,
|
| 735 |
+
"loss": 1.7446,
|
| 736 |
+
"step": 98000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 39.88432190456812,
|
| 740 |
+
"eval_loss": 1.7064162492752075,
|
| 741 |
+
"eval_runtime": 73.1495,
|
| 742 |
+
"eval_samples_per_second": 136.706,
|
| 743 |
+
"eval_steps_per_second": 2.146,
|
| 744 |
+
"step": 98000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 40.69793468308068,
|
| 748 |
+
"grad_norm": 13.10384750366211,
|
| 749 |
+
"learning_rate": 9.2999592999593e-06,
|
| 750 |
+
"loss": 1.7376,
|
| 751 |
+
"step": 100000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 40.69793468308068,
|
| 755 |
+
"eval_loss": 1.7068718671798706,
|
| 756 |
+
"eval_runtime": 73.1342,
|
| 757 |
+
"eval_samples_per_second": 136.735,
|
| 758 |
+
"eval_steps_per_second": 2.147,
|
| 759 |
+
"step": 100000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 41.511547461593246,
|
| 763 |
+
"grad_norm": 13.384297370910645,
|
| 764 |
+
"learning_rate": 8.485958485958487e-06,
|
| 765 |
+
"loss": 1.732,
|
| 766 |
+
"step": 102000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 41.511547461593246,
|
| 770 |
+
"eval_loss": 1.7083535194396973,
|
| 771 |
+
"eval_runtime": 73.1173,
|
| 772 |
+
"eval_samples_per_second": 136.767,
|
| 773 |
+
"eval_steps_per_second": 2.147,
|
| 774 |
+
"step": 102000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 42.32516024010581,
|
| 778 |
+
"grad_norm": 12.881793022155762,
|
| 779 |
+
"learning_rate": 7.671957671957672e-06,
|
| 780 |
+
"loss": 1.7282,
|
| 781 |
+
"step": 104000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 42.32516024010581,
|
| 785 |
+
"eval_loss": 1.7061749696731567,
|
| 786 |
+
"eval_runtime": 73.1059,
|
| 787 |
+
"eval_samples_per_second": 136.788,
|
| 788 |
+
"eval_steps_per_second": 2.148,
|
| 789 |
+
"step": 104000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 43.13877301861837,
|
| 793 |
+
"grad_norm": 13.3131685256958,
|
| 794 |
+
"learning_rate": 6.857956857956858e-06,
|
| 795 |
+
"loss": 1.7218,
|
| 796 |
+
"step": 106000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 43.13877301861837,
|
| 800 |
+
"eval_loss": 1.6910033226013184,
|
| 801 |
+
"eval_runtime": 73.0946,
|
| 802 |
+
"eval_samples_per_second": 136.809,
|
| 803 |
+
"eval_steps_per_second": 2.148,
|
| 804 |
+
"step": 106000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 43.9526910163801,
|
| 808 |
+
"grad_norm": 12.788925170898438,
|
| 809 |
+
"learning_rate": 6.043956043956044e-06,
|
| 810 |
+
"loss": 1.7205,
|
| 811 |
+
"step": 108000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 43.9526910163801,
|
| 815 |
+
"eval_loss": 1.6898643970489502,
|
| 816 |
+
"eval_runtime": 73.1074,
|
| 817 |
+
"eval_samples_per_second": 136.785,
|
| 818 |
+
"eval_steps_per_second": 2.148,
|
| 819 |
+
"step": 108000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 44.766303794892664,
|
| 823 |
+
"grad_norm": 12.509169578552246,
|
| 824 |
+
"learning_rate": 5.22995522995523e-06,
|
| 825 |
+
"loss": 1.7151,
|
| 826 |
+
"step": 110000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 44.766303794892664,
|
| 830 |
+
"eval_loss": 1.6873972415924072,
|
| 831 |
+
"eval_runtime": 73.1077,
|
| 832 |
+
"eval_samples_per_second": 136.784,
|
| 833 |
+
"eval_steps_per_second": 2.148,
|
| 834 |
+
"step": 110000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 45.57991657340523,
|
| 838 |
+
"grad_norm": 12.945860862731934,
|
| 839 |
+
"learning_rate": 4.415954415954416e-06,
|
| 840 |
+
"loss": 1.7109,
|
| 841 |
+
"step": 112000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 45.57991657340523,
|
| 845 |
+
"eval_loss": 1.677456021308899,
|
| 846 |
+
"eval_runtime": 73.1203,
|
| 847 |
+
"eval_samples_per_second": 136.761,
|
| 848 |
+
"eval_steps_per_second": 2.147,
|
| 849 |
+
"step": 112000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 46.39800590090548,
|
| 853 |
+
"grad_norm": 12.642820358276367,
|
| 854 |
+
"learning_rate": 3.6019536019536017e-06,
|
| 855 |
+
"loss": 1.7058,
|
| 856 |
+
"step": 114000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 46.39800590090548,
|
| 860 |
+
"eval_loss": 1.6775144338607788,
|
| 861 |
+
"eval_runtime": 73.1275,
|
| 862 |
+
"eval_samples_per_second": 136.747,
|
| 863 |
+
"eval_steps_per_second": 2.147,
|
| 864 |
+
"step": 114000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 47.21161867941805,
|
| 868 |
+
"grad_norm": 13.197073936462402,
|
| 869 |
+
"learning_rate": 2.787952787952788e-06,
|
| 870 |
+
"loss": 1.7048,
|
| 871 |
+
"step": 116000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 47.21161867941805,
|
| 875 |
+
"eval_loss": 1.6703945398330688,
|
| 876 |
+
"eval_runtime": 73.1574,
|
| 877 |
+
"eval_samples_per_second": 136.691,
|
| 878 |
+
"eval_steps_per_second": 2.146,
|
| 879 |
+
"step": 116000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 48.025231457930616,
|
| 883 |
+
"grad_norm": 12.470918655395508,
|
| 884 |
+
"learning_rate": 1.9739519739519742e-06,
|
| 885 |
+
"loss": 1.7037,
|
| 886 |
+
"step": 118000
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 48.025231457930616,
|
| 890 |
+
"eval_loss": 1.6824976205825806,
|
| 891 |
+
"eval_runtime": 73.1867,
|
| 892 |
+
"eval_samples_per_second": 136.637,
|
| 893 |
+
"eval_steps_per_second": 2.145,
|
| 894 |
+
"step": 118000
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 48.839149455692336,
|
| 898 |
+
"grad_norm": 12.579526901245117,
|
| 899 |
+
"learning_rate": 1.15995115995116e-06,
|
| 900 |
+
"loss": 1.6999,
|
| 901 |
+
"step": 120000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 48.839149455692336,
|
| 905 |
+
"eval_loss": 1.678907871246338,
|
| 906 |
+
"eval_runtime": 73.1871,
|
| 907 |
+
"eval_samples_per_second": 136.636,
|
| 908 |
+
"eval_steps_per_second": 2.145,
|
| 909 |
+
"step": 120000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 49.65276223420491,
|
| 913 |
+
"grad_norm": 13.10560131072998,
|
| 914 |
+
"learning_rate": 3.4595034595034596e-07,
|
| 915 |
+
"loss": 1.6969,
|
| 916 |
+
"step": 122000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 49.65276223420491,
|
| 920 |
+
"eval_loss": 1.6780418157577515,
|
| 921 |
+
"eval_runtime": 73.1913,
|
| 922 |
+
"eval_samples_per_second": 136.628,
|
| 923 |
+
"eval_steps_per_second": 2.145,
|
| 924 |
+
"step": 122000
|
| 925 |
+
}
|
| 926 |
+
],
|
| 927 |
+
"logging_steps": 2000,
|
| 928 |
+
"max_steps": 122850,
|
| 929 |
+
"num_input_tokens_seen": 0,
|
| 930 |
+
"num_train_epochs": 50,
|
| 931 |
+
"save_steps": 2000,
|
| 932 |
+
"stateful_callbacks": {
|
| 933 |
+
"TrainerControl": {
|
| 934 |
+
"args": {
|
| 935 |
+
"should_epoch_stop": false,
|
| 936 |
+
"should_evaluate": false,
|
| 937 |
+
"should_log": false,
|
| 938 |
+
"should_save": true,
|
| 939 |
+
"should_training_stop": true
|
| 940 |
+
},
|
| 941 |
+
"attributes": {}
|
| 942 |
+
}
|
| 943 |
+
},
|
| 944 |
+
"total_flos": 8.275195636696166e+18,
|
| 945 |
+
"train_batch_size": 32,
|
| 946 |
+
"trial_name": null,
|
| 947 |
+
"trial_params": null
|
| 948 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbb71f653a1b6b826aacd7f88afc300b683717cebac436ce22e3eba1a4f5fc19
|
| 3 |
+
size 5304
|