Commit
•
d71b63d
1
Parent(s):
e18d202
Training in progress, step 24500, checkpoint
Browse files- last-checkpoint/config.json +74 -0
- last-checkpoint/generation_config.json +13 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +756 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large",
|
| 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": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 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 |
+
"num_beams": 4,
|
| 47 |
+
"num_hidden_layers": 12,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.39.0.dev0",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
last-checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.39.0.dev0"
|
| 13 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:834c2455993182ac2454a775464049bea2f2b5240beb06e2feba3fb8c301fa17
|
| 3 |
+
size 1625426996
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a87cf4e69c66dbc19de741b9239037530ea89aa7d73f7a96d34e45b16e69901
|
| 3 |
+
size 3250759951
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d0e46e6068287fc01ac45a8b5e3fcdd19c9f45859f7367817e2d3fed4c37b2
|
| 3 |
+
size 14308
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20c09fe7581dfef8b1ef7b06f78a12ceb23770bd6828d148ea68eb51a6d9d6ff
|
| 3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,756 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.7116761207580566,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/lyrlen/bart/bart-finetuned-lyrlen-512/checkpoint-22500",
|
| 4 |
+
"epoch": 2.0416666666666665,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 2.445735216140747,
|
| 14 |
+
"learning_rate": 4.8958333333333335e-05,
|
| 15 |
+
"loss": 2.221,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"eval_loss": 1.966707706451416,
|
| 21 |
+
"eval_runtime": 523.1555,
|
| 22 |
+
"eval_samples_per_second": 5.734,
|
| 23 |
+
"eval_steps_per_second": 2.867,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08,
|
| 28 |
+
"grad_norm": 2.755873680114746,
|
| 29 |
+
"learning_rate": 4.791666666666667e-05,
|
| 30 |
+
"loss": 2.0336,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"eval_loss": 1.8762251138687134,
|
| 36 |
+
"eval_runtime": 521.8304,
|
| 37 |
+
"eval_samples_per_second": 5.749,
|
| 38 |
+
"eval_steps_per_second": 2.874,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.12,
|
| 43 |
+
"grad_norm": 1.6574139595031738,
|
| 44 |
+
"learning_rate": 4.6875e-05,
|
| 45 |
+
"loss": 1.9563,
|
| 46 |
+
"step": 1500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.12,
|
| 50 |
+
"eval_loss": 1.8565189838409424,
|
| 51 |
+
"eval_runtime": 523.2148,
|
| 52 |
+
"eval_samples_per_second": 5.734,
|
| 53 |
+
"eval_steps_per_second": 2.867,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.17,
|
| 58 |
+
"grad_norm": 2.1005289554595947,
|
| 59 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 60 |
+
"loss": 1.9555,
|
| 61 |
+
"step": 2000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.17,
|
| 65 |
+
"eval_loss": 1.8391904830932617,
|
| 66 |
+
"eval_runtime": 523.6661,
|
| 67 |
+
"eval_samples_per_second": 5.729,
|
| 68 |
+
"eval_steps_per_second": 2.864,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"grad_norm": 2.272672414779663,
|
| 74 |
+
"learning_rate": 4.4791666666666673e-05,
|
| 75 |
+
"loss": 1.9072,
|
| 76 |
+
"step": 2500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.21,
|
| 80 |
+
"eval_loss": 1.8213719129562378,
|
| 81 |
+
"eval_runtime": 522.7152,
|
| 82 |
+
"eval_samples_per_second": 5.739,
|
| 83 |
+
"eval_steps_per_second": 2.87,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.25,
|
| 88 |
+
"grad_norm": 2.835890769958496,
|
| 89 |
+
"learning_rate": 4.375e-05,
|
| 90 |
+
"loss": 1.8796,
|
| 91 |
+
"step": 3000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.25,
|
| 95 |
+
"eval_loss": 1.8246040344238281,
|
| 96 |
+
"eval_runtime": 523.1839,
|
| 97 |
+
"eval_samples_per_second": 5.734,
|
| 98 |
+
"eval_steps_per_second": 2.867,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.29,
|
| 103 |
+
"grad_norm": 3.6644091606140137,
|
| 104 |
+
"learning_rate": 4.270833333333333e-05,
|
| 105 |
+
"loss": 1.8955,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.29,
|
| 110 |
+
"eval_loss": 1.8050193786621094,
|
| 111 |
+
"eval_runtime": 523.9576,
|
| 112 |
+
"eval_samples_per_second": 5.726,
|
| 113 |
+
"eval_steps_per_second": 2.863,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.33,
|
| 118 |
+
"grad_norm": 3.492926836013794,
|
| 119 |
+
"learning_rate": 4.166666666666667e-05,
|
| 120 |
+
"loss": 1.8254,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.33,
|
| 125 |
+
"eval_loss": 1.806920051574707,
|
| 126 |
+
"eval_runtime": 522.6132,
|
| 127 |
+
"eval_samples_per_second": 5.74,
|
| 128 |
+
"eval_steps_per_second": 2.87,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.38,
|
| 133 |
+
"grad_norm": 2.235563278198242,
|
| 134 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 135 |
+
"loss": 1.8518,
|
| 136 |
+
"step": 4500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.38,
|
| 140 |
+
"eval_loss": 1.7872947454452515,
|
| 141 |
+
"eval_runtime": 521.8198,
|
| 142 |
+
"eval_samples_per_second": 5.749,
|
| 143 |
+
"eval_steps_per_second": 2.875,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.42,
|
| 148 |
+
"grad_norm": 3.2742645740509033,
|
| 149 |
+
"learning_rate": 3.958333333333333e-05,
|
| 150 |
+
"loss": 1.8471,
|
| 151 |
+
"step": 5000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.42,
|
| 155 |
+
"eval_loss": 1.7879706621170044,
|
| 156 |
+
"eval_runtime": 522.5919,
|
| 157 |
+
"eval_samples_per_second": 5.741,
|
| 158 |
+
"eval_steps_per_second": 2.87,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.46,
|
| 163 |
+
"grad_norm": 2.861785411834717,
|
| 164 |
+
"learning_rate": 3.854166666666667e-05,
|
| 165 |
+
"loss": 1.8536,
|
| 166 |
+
"step": 5500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.46,
|
| 170 |
+
"eval_loss": 1.773565649986267,
|
| 171 |
+
"eval_runtime": 522.5748,
|
| 172 |
+
"eval_samples_per_second": 5.741,
|
| 173 |
+
"eval_steps_per_second": 2.87,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.5,
|
| 178 |
+
"grad_norm": 2.342087745666504,
|
| 179 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 180 |
+
"loss": 1.8075,
|
| 181 |
+
"step": 6000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.5,
|
| 185 |
+
"eval_loss": 1.7772246599197388,
|
| 186 |
+
"eval_runtime": 521.8614,
|
| 187 |
+
"eval_samples_per_second": 5.749,
|
| 188 |
+
"eval_steps_per_second": 2.874,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.54,
|
| 193 |
+
"grad_norm": 3.7963709831237793,
|
| 194 |
+
"learning_rate": 3.6458333333333336e-05,
|
| 195 |
+
"loss": 1.8143,
|
| 196 |
+
"step": 6500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.54,
|
| 200 |
+
"eval_loss": 1.7724062204360962,
|
| 201 |
+
"eval_runtime": 522.2168,
|
| 202 |
+
"eval_samples_per_second": 5.745,
|
| 203 |
+
"eval_steps_per_second": 2.872,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.58,
|
| 208 |
+
"grad_norm": 2.7261409759521484,
|
| 209 |
+
"learning_rate": 3.541666666666667e-05,
|
| 210 |
+
"loss": 1.8383,
|
| 211 |
+
"step": 7000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.58,
|
| 215 |
+
"eval_loss": 1.7670141458511353,
|
| 216 |
+
"eval_runtime": 523.5327,
|
| 217 |
+
"eval_samples_per_second": 5.73,
|
| 218 |
+
"eval_steps_per_second": 2.865,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.62,
|
| 223 |
+
"grad_norm": 2.521083354949951,
|
| 224 |
+
"learning_rate": 3.4375e-05,
|
| 225 |
+
"loss": 1.746,
|
| 226 |
+
"step": 7500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.62,
|
| 230 |
+
"eval_loss": 1.774078607559204,
|
| 231 |
+
"eval_runtime": 522.8622,
|
| 232 |
+
"eval_samples_per_second": 5.738,
|
| 233 |
+
"eval_steps_per_second": 2.869,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.67,
|
| 238 |
+
"grad_norm": 2.275449752807617,
|
| 239 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 240 |
+
"loss": 1.7844,
|
| 241 |
+
"step": 8000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.67,
|
| 245 |
+
"eval_loss": 1.7608264684677124,
|
| 246 |
+
"eval_runtime": 524.0843,
|
| 247 |
+
"eval_samples_per_second": 5.724,
|
| 248 |
+
"eval_steps_per_second": 2.862,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.71,
|
| 253 |
+
"grad_norm": 3.3412251472473145,
|
| 254 |
+
"learning_rate": 3.229166666666667e-05,
|
| 255 |
+
"loss": 1.7761,
|
| 256 |
+
"step": 8500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.71,
|
| 260 |
+
"eval_loss": 1.7679654359817505,
|
| 261 |
+
"eval_runtime": 523.8138,
|
| 262 |
+
"eval_samples_per_second": 5.727,
|
| 263 |
+
"eval_steps_per_second": 2.864,
|
| 264 |
+
"step": 8500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.75,
|
| 268 |
+
"grad_norm": 2.000788688659668,
|
| 269 |
+
"learning_rate": 3.125e-05,
|
| 270 |
+
"loss": 1.7367,
|
| 271 |
+
"step": 9000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.75,
|
| 275 |
+
"eval_loss": 1.7554887533187866,
|
| 276 |
+
"eval_runtime": 522.9431,
|
| 277 |
+
"eval_samples_per_second": 5.737,
|
| 278 |
+
"eval_steps_per_second": 2.868,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.79,
|
| 283 |
+
"grad_norm": 2.744258403778076,
|
| 284 |
+
"learning_rate": 3.0208333333333334e-05,
|
| 285 |
+
"loss": 1.7656,
|
| 286 |
+
"step": 9500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.79,
|
| 290 |
+
"eval_loss": 1.7508151531219482,
|
| 291 |
+
"eval_runtime": 522.4025,
|
| 292 |
+
"eval_samples_per_second": 5.743,
|
| 293 |
+
"eval_steps_per_second": 2.871,
|
| 294 |
+
"step": 9500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.83,
|
| 298 |
+
"grad_norm": 2.7946290969848633,
|
| 299 |
+
"learning_rate": 2.916666666666667e-05,
|
| 300 |
+
"loss": 1.7467,
|
| 301 |
+
"step": 10000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.83,
|
| 305 |
+
"eval_loss": 1.7557835578918457,
|
| 306 |
+
"eval_runtime": 523.7331,
|
| 307 |
+
"eval_samples_per_second": 5.728,
|
| 308 |
+
"eval_steps_per_second": 2.864,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.88,
|
| 313 |
+
"grad_norm": 2.4864296913146973,
|
| 314 |
+
"learning_rate": 2.8125000000000003e-05,
|
| 315 |
+
"loss": 1.7744,
|
| 316 |
+
"step": 10500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.88,
|
| 320 |
+
"eval_loss": 1.744908094406128,
|
| 321 |
+
"eval_runtime": 523.6435,
|
| 322 |
+
"eval_samples_per_second": 5.729,
|
| 323 |
+
"eval_steps_per_second": 2.865,
|
| 324 |
+
"step": 10500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.92,
|
| 328 |
+
"grad_norm": 2.4293007850646973,
|
| 329 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 330 |
+
"loss": 1.7513,
|
| 331 |
+
"step": 11000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.92,
|
| 335 |
+
"eval_loss": 1.7462434768676758,
|
| 336 |
+
"eval_runtime": 523.5176,
|
| 337 |
+
"eval_samples_per_second": 5.73,
|
| 338 |
+
"eval_steps_per_second": 2.865,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.96,
|
| 343 |
+
"grad_norm": 2.8948864936828613,
|
| 344 |
+
"learning_rate": 2.604166666666667e-05,
|
| 345 |
+
"loss": 1.7482,
|
| 346 |
+
"step": 11500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.96,
|
| 350 |
+
"eval_loss": 1.757570505142212,
|
| 351 |
+
"eval_runtime": 523.9557,
|
| 352 |
+
"eval_samples_per_second": 5.726,
|
| 353 |
+
"eval_steps_per_second": 2.863,
|
| 354 |
+
"step": 11500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.0,
|
| 358 |
+
"grad_norm": 3.327749490737915,
|
| 359 |
+
"learning_rate": 2.5e-05,
|
| 360 |
+
"loss": 1.724,
|
| 361 |
+
"step": 12000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.0,
|
| 365 |
+
"eval_loss": 1.752493143081665,
|
| 366 |
+
"eval_runtime": 523.6941,
|
| 367 |
+
"eval_samples_per_second": 5.729,
|
| 368 |
+
"eval_steps_per_second": 2.864,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.04,
|
| 373 |
+
"grad_norm": 2.6060996055603027,
|
| 374 |
+
"learning_rate": 2.3958333333333334e-05,
|
| 375 |
+
"loss": 1.7043,
|
| 376 |
+
"step": 12500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.04,
|
| 380 |
+
"eval_loss": 1.7745699882507324,
|
| 381 |
+
"eval_runtime": 524.2816,
|
| 382 |
+
"eval_samples_per_second": 5.722,
|
| 383 |
+
"eval_steps_per_second": 2.861,
|
| 384 |
+
"step": 12500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.08,
|
| 388 |
+
"grad_norm": 3.1417739391326904,
|
| 389 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 390 |
+
"loss": 1.6869,
|
| 391 |
+
"step": 13000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.08,
|
| 395 |
+
"eval_loss": 1.7530784606933594,
|
| 396 |
+
"eval_runtime": 524.8963,
|
| 397 |
+
"eval_samples_per_second": 5.715,
|
| 398 |
+
"eval_steps_per_second": 2.858,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.12,
|
| 403 |
+
"grad_norm": 2.0913174152374268,
|
| 404 |
+
"learning_rate": 2.1875e-05,
|
| 405 |
+
"loss": 1.7405,
|
| 406 |
+
"step": 13500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.12,
|
| 410 |
+
"eval_loss": 1.7472872734069824,
|
| 411 |
+
"eval_runtime": 523.5132,
|
| 412 |
+
"eval_samples_per_second": 5.731,
|
| 413 |
+
"eval_steps_per_second": 2.865,
|
| 414 |
+
"step": 13500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.17,
|
| 418 |
+
"grad_norm": 2.501850128173828,
|
| 419 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 420 |
+
"loss": 1.7343,
|
| 421 |
+
"step": 14000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.17,
|
| 425 |
+
"eval_loss": 1.73961341381073,
|
| 426 |
+
"eval_runtime": 523.4238,
|
| 427 |
+
"eval_samples_per_second": 5.731,
|
| 428 |
+
"eval_steps_per_second": 2.866,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.21,
|
| 433 |
+
"grad_norm": 2.3180103302001953,
|
| 434 |
+
"learning_rate": 1.9791666666666665e-05,
|
| 435 |
+
"loss": 1.649,
|
| 436 |
+
"step": 14500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.21,
|
| 440 |
+
"eval_loss": 1.738362431526184,
|
| 441 |
+
"eval_runtime": 522.9782,
|
| 442 |
+
"eval_samples_per_second": 5.736,
|
| 443 |
+
"eval_steps_per_second": 2.868,
|
| 444 |
+
"step": 14500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.25,
|
| 448 |
+
"grad_norm": 2.6544899940490723,
|
| 449 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 450 |
+
"loss": 1.7208,
|
| 451 |
+
"step": 15000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.25,
|
| 455 |
+
"eval_loss": 1.7367714643478394,
|
| 456 |
+
"eval_runtime": 522.0439,
|
| 457 |
+
"eval_samples_per_second": 5.747,
|
| 458 |
+
"eval_steps_per_second": 2.873,
|
| 459 |
+
"step": 15000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.29,
|
| 463 |
+
"grad_norm": 2.5193896293640137,
|
| 464 |
+
"learning_rate": 1.7708333333333335e-05,
|
| 465 |
+
"loss": 1.6931,
|
| 466 |
+
"step": 15500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.29,
|
| 470 |
+
"eval_loss": 1.7404463291168213,
|
| 471 |
+
"eval_runtime": 523.0385,
|
| 472 |
+
"eval_samples_per_second": 5.736,
|
| 473 |
+
"eval_steps_per_second": 2.868,
|
| 474 |
+
"step": 15500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.33,
|
| 478 |
+
"grad_norm": 2.3002140522003174,
|
| 479 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 480 |
+
"loss": 1.5941,
|
| 481 |
+
"step": 16000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.33,
|
| 485 |
+
"eval_loss": 1.8222692012786865,
|
| 486 |
+
"eval_runtime": 521.374,
|
| 487 |
+
"eval_samples_per_second": 5.754,
|
| 488 |
+
"eval_steps_per_second": 2.877,
|
| 489 |
+
"step": 16000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.38,
|
| 493 |
+
"grad_norm": 3.3250951766967773,
|
| 494 |
+
"learning_rate": 1.5625e-05,
|
| 495 |
+
"loss": 1.6651,
|
| 496 |
+
"step": 16500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.38,
|
| 500 |
+
"eval_loss": 1.728702187538147,
|
| 501 |
+
"eval_runtime": 522.2011,
|
| 502 |
+
"eval_samples_per_second": 5.745,
|
| 503 |
+
"eval_steps_per_second": 2.872,
|
| 504 |
+
"step": 16500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.42,
|
| 508 |
+
"grad_norm": 2.0962421894073486,
|
| 509 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 510 |
+
"loss": 1.6649,
|
| 511 |
+
"step": 17000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.42,
|
| 515 |
+
"eval_loss": 1.741267204284668,
|
| 516 |
+
"eval_runtime": 522.024,
|
| 517 |
+
"eval_samples_per_second": 5.747,
|
| 518 |
+
"eval_steps_per_second": 2.873,
|
| 519 |
+
"step": 17000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.46,
|
| 523 |
+
"grad_norm": 2.672060012817383,
|
| 524 |
+
"learning_rate": 1.3541666666666666e-05,
|
| 525 |
+
"loss": 1.7108,
|
| 526 |
+
"step": 17500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.46,
|
| 530 |
+
"eval_loss": 1.7304407358169556,
|
| 531 |
+
"eval_runtime": 521.9513,
|
| 532 |
+
"eval_samples_per_second": 5.748,
|
| 533 |
+
"eval_steps_per_second": 2.874,
|
| 534 |
+
"step": 17500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.5,
|
| 538 |
+
"grad_norm": 2.358701229095459,
|
| 539 |
+
"learning_rate": 1.25e-05,
|
| 540 |
+
"loss": 1.713,
|
| 541 |
+
"step": 18000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.5,
|
| 545 |
+
"eval_loss": 1.7263309955596924,
|
| 546 |
+
"eval_runtime": 521.5686,
|
| 547 |
+
"eval_samples_per_second": 5.752,
|
| 548 |
+
"eval_steps_per_second": 2.876,
|
| 549 |
+
"step": 18000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.54,
|
| 553 |
+
"grad_norm": 3.01208233833313,
|
| 554 |
+
"learning_rate": 1.1458333333333333e-05,
|
| 555 |
+
"loss": 1.6866,
|
| 556 |
+
"step": 18500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.54,
|
| 560 |
+
"eval_loss": 1.7139294147491455,
|
| 561 |
+
"eval_runtime": 521.9607,
|
| 562 |
+
"eval_samples_per_second": 5.748,
|
| 563 |
+
"eval_steps_per_second": 2.874,
|
| 564 |
+
"step": 18500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.58,
|
| 568 |
+
"grad_norm": 1.647988200187683,
|
| 569 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 570 |
+
"loss": 1.6461,
|
| 571 |
+
"step": 19000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.58,
|
| 575 |
+
"eval_loss": 1.7220714092254639,
|
| 576 |
+
"eval_runtime": 523.0668,
|
| 577 |
+
"eval_samples_per_second": 5.735,
|
| 578 |
+
"eval_steps_per_second": 2.868,
|
| 579 |
+
"step": 19000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.62,
|
| 583 |
+
"grad_norm": 2.259550094604492,
|
| 584 |
+
"learning_rate": 9.375000000000001e-06,
|
| 585 |
+
"loss": 1.6886,
|
| 586 |
+
"step": 19500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.62,
|
| 590 |
+
"eval_loss": 1.7159427404403687,
|
| 591 |
+
"eval_runtime": 522.0391,
|
| 592 |
+
"eval_samples_per_second": 5.747,
|
| 593 |
+
"eval_steps_per_second": 2.873,
|
| 594 |
+
"step": 19500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.67,
|
| 598 |
+
"grad_norm": 2.249917507171631,
|
| 599 |
+
"learning_rate": 8.333333333333334e-06,
|
| 600 |
+
"loss": 1.6511,
|
| 601 |
+
"step": 20000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.67,
|
| 605 |
+
"eval_loss": 1.7302324771881104,
|
| 606 |
+
"eval_runtime": 521.3364,
|
| 607 |
+
"eval_samples_per_second": 5.754,
|
| 608 |
+
"eval_steps_per_second": 2.877,
|
| 609 |
+
"step": 20000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.71,
|
| 613 |
+
"grad_norm": 1.9024745225906372,
|
| 614 |
+
"learning_rate": 7.2916666666666674e-06,
|
| 615 |
+
"loss": 1.6626,
|
| 616 |
+
"step": 20500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.71,
|
| 620 |
+
"eval_loss": 1.7181695699691772,
|
| 621 |
+
"eval_runtime": 489.9754,
|
| 622 |
+
"eval_samples_per_second": 6.123,
|
| 623 |
+
"eval_steps_per_second": 3.061,
|
| 624 |
+
"step": 20500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.75,
|
| 628 |
+
"grad_norm": 2.484917640686035,
|
| 629 |
+
"learning_rate": 6.25e-06,
|
| 630 |
+
"loss": 1.7052,
|
| 631 |
+
"step": 21000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.75,
|
| 635 |
+
"eval_loss": 1.716320514678955,
|
| 636 |
+
"eval_runtime": 489.0607,
|
| 637 |
+
"eval_samples_per_second": 6.134,
|
| 638 |
+
"eval_steps_per_second": 3.067,
|
| 639 |
+
"step": 21000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.79,
|
| 643 |
+
"grad_norm": 2.4450478553771973,
|
| 644 |
+
"learning_rate": 5.208333333333334e-06,
|
| 645 |
+
"loss": 1.6831,
|
| 646 |
+
"step": 21500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.79,
|
| 650 |
+
"eval_loss": 1.7168132066726685,
|
| 651 |
+
"eval_runtime": 489.1379,
|
| 652 |
+
"eval_samples_per_second": 6.133,
|
| 653 |
+
"eval_steps_per_second": 3.067,
|
| 654 |
+
"step": 21500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.83,
|
| 658 |
+
"grad_norm": 2.011652946472168,
|
| 659 |
+
"learning_rate": 4.166666666666667e-06,
|
| 660 |
+
"loss": 1.6057,
|
| 661 |
+
"step": 22000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.83,
|
| 665 |
+
"eval_loss": 1.715084195137024,
|
| 666 |
+
"eval_runtime": 489.2379,
|
| 667 |
+
"eval_samples_per_second": 6.132,
|
| 668 |
+
"eval_steps_per_second": 3.066,
|
| 669 |
+
"step": 22000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.88,
|
| 673 |
+
"grad_norm": 1.7278447151184082,
|
| 674 |
+
"learning_rate": 3.125e-06,
|
| 675 |
+
"loss": 1.6761,
|
| 676 |
+
"step": 22500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.88,
|
| 680 |
+
"eval_loss": 1.7116761207580566,
|
| 681 |
+
"eval_runtime": 488.632,
|
| 682 |
+
"eval_samples_per_second": 6.14,
|
| 683 |
+
"eval_steps_per_second": 3.07,
|
| 684 |
+
"step": 22500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.92,
|
| 688 |
+
"grad_norm": 1.4899113178253174,
|
| 689 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 690 |
+
"loss": 1.6668,
|
| 691 |
+
"step": 23000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.92,
|
| 695 |
+
"eval_loss": 1.7163901329040527,
|
| 696 |
+
"eval_runtime": 488.958,
|
| 697 |
+
"eval_samples_per_second": 6.135,
|
| 698 |
+
"eval_steps_per_second": 3.068,
|
| 699 |
+
"step": 23000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.96,
|
| 703 |
+
"grad_norm": 2.4776082038879395,
|
| 704 |
+
"learning_rate": 1.0416666666666667e-06,
|
| 705 |
+
"loss": 1.612,
|
| 706 |
+
"step": 23500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.96,
|
| 710 |
+
"eval_loss": 1.712184190750122,
|
| 711 |
+
"eval_runtime": 490.7154,
|
| 712 |
+
"eval_samples_per_second": 6.114,
|
| 713 |
+
"eval_steps_per_second": 3.057,
|
| 714 |
+
"step": 23500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.0,
|
| 718 |
+
"grad_norm": 1.9447611570358276,
|
| 719 |
+
"learning_rate": 0.0,
|
| 720 |
+
"loss": 1.6617,
|
| 721 |
+
"step": 24000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.0,
|
| 725 |
+
"eval_loss": 1.7131377458572388,
|
| 726 |
+
"eval_runtime": 488.7943,
|
| 727 |
+
"eval_samples_per_second": 6.138,
|
| 728 |
+
"eval_steps_per_second": 3.069,
|
| 729 |
+
"step": 24000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.04,
|
| 733 |
+
"grad_norm": 1.3564224243164062,
|
| 734 |
+
"learning_rate": 1.597222222222222e-05,
|
| 735 |
+
"loss": 1.641,
|
| 736 |
+
"step": 24500
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.04,
|
| 740 |
+
"eval_loss": 1.727720856666565,
|
| 741 |
+
"eval_runtime": 492.4028,
|
| 742 |
+
"eval_samples_per_second": 6.093,
|
| 743 |
+
"eval_steps_per_second": 3.046,
|
| 744 |
+
"step": 24500
|
| 745 |
+
}
|
| 746 |
+
],
|
| 747 |
+
"logging_steps": 500,
|
| 748 |
+
"max_steps": 36000,
|
| 749 |
+
"num_input_tokens_seen": 0,
|
| 750 |
+
"num_train_epochs": 3,
|
| 751 |
+
"save_steps": 500,
|
| 752 |
+
"total_flos": 5.3094062751744e+16,
|
| 753 |
+
"train_batch_size": 2,
|
| 754 |
+
"trial_name": null,
|
| 755 |
+
"trial_params": null
|
| 756 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d59b57789e0457cbbcc4731527b4fc44795495c0fbfa437c26e4d33bbfb9bbb4
|
| 3 |
+
size 5368
|