Upload 8 files
Browse files- config.json +107 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1456 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": "58597eee6783b5d4405df333573fe4b4368bce29",
|
| 3 |
+
"_name_or_path": "microsoft/git-large",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GitForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 101,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 102,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"max_position_embeddings": 1024,
|
| 18 |
+
"model_type": "git",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 6,
|
| 21 |
+
"num_image_with_embedding": null,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": null,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vision_config": {
|
| 29 |
+
"_name_or_path": "",
|
| 30 |
+
"add_cross_attention": false,
|
| 31 |
+
"architectures": null,
|
| 32 |
+
"attention_dropout": 0.0,
|
| 33 |
+
"bad_words_ids": null,
|
| 34 |
+
"begin_suppress_tokens": null,
|
| 35 |
+
"bos_token_id": null,
|
| 36 |
+
"chunk_size_feed_forward": 0,
|
| 37 |
+
"cross_attention_hidden_size": null,
|
| 38 |
+
"decoder_start_token_id": null,
|
| 39 |
+
"diversity_penalty": 0.0,
|
| 40 |
+
"do_sample": false,
|
| 41 |
+
"dropout": 0.0,
|
| 42 |
+
"early_stopping": false,
|
| 43 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 44 |
+
"eos_token_id": null,
|
| 45 |
+
"exponential_decay_length_penalty": null,
|
| 46 |
+
"finetuning_task": null,
|
| 47 |
+
"forced_bos_token_id": null,
|
| 48 |
+
"forced_eos_token_id": null,
|
| 49 |
+
"hidden_act": "quick_gelu",
|
| 50 |
+
"hidden_size": 1024,
|
| 51 |
+
"id2label": {
|
| 52 |
+
"0": "LABEL_0",
|
| 53 |
+
"1": "LABEL_1"
|
| 54 |
+
},
|
| 55 |
+
"image_size": 224,
|
| 56 |
+
"initializer_factor": 1.0,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"intermediate_size": 4096,
|
| 59 |
+
"is_decoder": false,
|
| 60 |
+
"is_encoder_decoder": false,
|
| 61 |
+
"label2id": {
|
| 62 |
+
"LABEL_0": 0,
|
| 63 |
+
"LABEL_1": 1
|
| 64 |
+
},
|
| 65 |
+
"layer_norm_eps": 1e-05,
|
| 66 |
+
"length_penalty": 1.0,
|
| 67 |
+
"max_length": 20,
|
| 68 |
+
"min_length": 0,
|
| 69 |
+
"model_type": "git_vision_model",
|
| 70 |
+
"no_repeat_ngram_size": 0,
|
| 71 |
+
"num_attention_heads": 16,
|
| 72 |
+
"num_beam_groups": 1,
|
| 73 |
+
"num_beams": 1,
|
| 74 |
+
"num_channels": 3,
|
| 75 |
+
"num_hidden_layers": 24,
|
| 76 |
+
"num_return_sequences": 1,
|
| 77 |
+
"output_attentions": false,
|
| 78 |
+
"output_hidden_states": false,
|
| 79 |
+
"output_scores": false,
|
| 80 |
+
"pad_token_id": null,
|
| 81 |
+
"patch_size": 14,
|
| 82 |
+
"prefix": null,
|
| 83 |
+
"problem_type": null,
|
| 84 |
+
"projection_dim": 512,
|
| 85 |
+
"pruned_heads": {},
|
| 86 |
+
"remove_invalid_values": false,
|
| 87 |
+
"repetition_penalty": 1.0,
|
| 88 |
+
"return_dict": true,
|
| 89 |
+
"return_dict_in_generate": false,
|
| 90 |
+
"sep_token_id": null,
|
| 91 |
+
"suppress_tokens": null,
|
| 92 |
+
"task_specific_params": null,
|
| 93 |
+
"temperature": 1.0,
|
| 94 |
+
"tf_legacy_loss": false,
|
| 95 |
+
"tie_encoder_decoder": false,
|
| 96 |
+
"tie_word_embeddings": true,
|
| 97 |
+
"tokenizer_class": null,
|
| 98 |
+
"top_k": 50,
|
| 99 |
+
"top_p": 1.0,
|
| 100 |
+
"torch_dtype": null,
|
| 101 |
+
"torchscript": false,
|
| 102 |
+
"transformers_version": "4.32.0.dev0",
|
| 103 |
+
"typical_p": 1.0,
|
| 104 |
+
"use_bfloat16": false
|
| 105 |
+
},
|
| 106 |
+
"vocab_size": 30522
|
| 107 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 101,
|
| 4 |
+
"eos_token_id": 102,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.32.0.dev0"
|
| 7 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8f88690ce4cb3c310c86ec319617844d19c78247a627a132d19f97f96bbbc73
|
| 3 |
+
size 3153984176
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddc607ddcb2e34d19a8244f5a3643d1152e2412bed84faec45b52dd4326e6e9b
|
| 3 |
+
size 1576962129
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a62db230c38543114287662eb01e9fc406764e79db440c27ce85d2818ef7c556
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61649215f1c8d228a8f096401009ad3ee0a9db2130083b6b0a45418ca473ebac
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1456 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3793087899684906,
|
| 3 |
+
"best_model_checkpoint": "/data/users/yanyang/Projects/COCO_Caption_Refine/debug/git/2023-09-11-23-23-40/checkpoint-4800",
|
| 4 |
+
"epoch": 2.9702970297029703,
|
| 5 |
+
"global_step": 4800,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.948432343234324e-05,
|
| 13 |
+
"loss": 6.0088,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"eval_loss": 2.9973134994506836,
|
| 19 |
+
"eval_runtime": 2.3906,
|
| 20 |
+
"eval_samples_per_second": 13.386,
|
| 21 |
+
"eval_steps_per_second": 6.693,
|
| 22 |
+
"eval_wer_score": 3.802087864288821,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06,
|
| 27 |
+
"learning_rate": 4.8968646864686466e-05,
|
| 28 |
+
"loss": 1.3576,
|
| 29 |
+
"step": 100
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.06,
|
| 33 |
+
"eval_loss": 0.5444818139076233,
|
| 34 |
+
"eval_runtime": 2.2435,
|
| 35 |
+
"eval_samples_per_second": 14.264,
|
| 36 |
+
"eval_steps_per_second": 7.132,
|
| 37 |
+
"eval_wer_score": 3.5702479338842976,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 4.8452970297029704e-05,
|
| 43 |
+
"loss": 0.5214,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09,
|
| 48 |
+
"eval_loss": 0.4757494628429413,
|
| 49 |
+
"eval_runtime": 2.3157,
|
| 50 |
+
"eval_samples_per_second": 13.818,
|
| 51 |
+
"eval_steps_per_second": 6.909,
|
| 52 |
+
"eval_wer_score": 4.052196607220531,
|
| 53 |
+
"step": 150
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.12,
|
| 57 |
+
"learning_rate": 4.793729372937294e-05,
|
| 58 |
+
"loss": 0.4845,
|
| 59 |
+
"step": 200
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.12,
|
| 63 |
+
"eval_loss": 0.4562256336212158,
|
| 64 |
+
"eval_runtime": 2.3849,
|
| 65 |
+
"eval_samples_per_second": 13.418,
|
| 66 |
+
"eval_steps_per_second": 6.709,
|
| 67 |
+
"eval_wer_score": 4.051326663766855,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"learning_rate": 4.7421617161716174e-05,
|
| 73 |
+
"loss": 0.4694,
|
| 74 |
+
"step": 250
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15,
|
| 78 |
+
"eval_loss": 0.4434777796268463,
|
| 79 |
+
"eval_runtime": 2.3886,
|
| 80 |
+
"eval_samples_per_second": 13.397,
|
| 81 |
+
"eval_steps_per_second": 6.698,
|
| 82 |
+
"eval_wer_score": 4.0582862113962594,
|
| 83 |
+
"step": 250
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.19,
|
| 87 |
+
"learning_rate": 4.6905940594059406e-05,
|
| 88 |
+
"loss": 0.4598,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.19,
|
| 93 |
+
"eval_loss": 0.43529027700424194,
|
| 94 |
+
"eval_runtime": 2.3401,
|
| 95 |
+
"eval_samples_per_second": 13.674,
|
| 96 |
+
"eval_steps_per_second": 6.837,
|
| 97 |
+
"eval_wer_score": 4.02131361461505,
|
| 98 |
+
"step": 300
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.22,
|
| 102 |
+
"learning_rate": 4.6390264026402644e-05,
|
| 103 |
+
"loss": 0.4499,
|
| 104 |
+
"step": 350
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.22,
|
| 108 |
+
"eval_loss": 0.4303966462612152,
|
| 109 |
+
"eval_runtime": 2.386,
|
| 110 |
+
"eval_samples_per_second": 13.412,
|
| 111 |
+
"eval_steps_per_second": 6.706,
|
| 112 |
+
"eval_wer_score": 4.097433666811657,
|
| 113 |
+
"step": 350
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.25,
|
| 117 |
+
"learning_rate": 4.5874587458745876e-05,
|
| 118 |
+
"loss": 0.4444,
|
| 119 |
+
"step": 400
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.25,
|
| 123 |
+
"eval_loss": 0.4260537624359131,
|
| 124 |
+
"eval_runtime": 2.2892,
|
| 125 |
+
"eval_samples_per_second": 13.979,
|
| 126 |
+
"eval_steps_per_second": 6.989,
|
| 127 |
+
"eval_wer_score": 4.073510221835581,
|
| 128 |
+
"step": 400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.28,
|
| 132 |
+
"learning_rate": 4.5358910891089114e-05,
|
| 133 |
+
"loss": 0.4419,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.28,
|
| 138 |
+
"eval_loss": 0.4221154451370239,
|
| 139 |
+
"eval_runtime": 2.3303,
|
| 140 |
+
"eval_samples_per_second": 13.732,
|
| 141 |
+
"eval_steps_per_second": 6.866,
|
| 142 |
+
"eval_wer_score": 4.101348412353197,
|
| 143 |
+
"step": 450
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.31,
|
| 147 |
+
"learning_rate": 4.4843234323432346e-05,
|
| 148 |
+
"loss": 0.439,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.31,
|
| 153 |
+
"eval_loss": 0.42153507471084595,
|
| 154 |
+
"eval_runtime": 2.3513,
|
| 155 |
+
"eval_samples_per_second": 13.61,
|
| 156 |
+
"eval_steps_per_second": 6.805,
|
| 157 |
+
"eval_wer_score": 4.062200956937799,
|
| 158 |
+
"step": 500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.34,
|
| 162 |
+
"learning_rate": 4.432755775577558e-05,
|
| 163 |
+
"loss": 0.4339,
|
| 164 |
+
"step": 550
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.34,
|
| 168 |
+
"eval_loss": 0.42045870423316956,
|
| 169 |
+
"eval_runtime": 2.2803,
|
| 170 |
+
"eval_samples_per_second": 14.034,
|
| 171 |
+
"eval_steps_per_second": 7.017,
|
| 172 |
+
"eval_wer_score": 4.056546324488909,
|
| 173 |
+
"step": 550
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.37,
|
| 177 |
+
"learning_rate": 4.3811881188118816e-05,
|
| 178 |
+
"loss": 0.4295,
|
| 179 |
+
"step": 600
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.37,
|
| 183 |
+
"eval_loss": 0.4192642569541931,
|
| 184 |
+
"eval_runtime": 2.3998,
|
| 185 |
+
"eval_samples_per_second": 13.335,
|
| 186 |
+
"eval_steps_per_second": 6.667,
|
| 187 |
+
"eval_wer_score": 4.061765985210961,
|
| 188 |
+
"step": 600
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.4,
|
| 192 |
+
"learning_rate": 4.329620462046205e-05,
|
| 193 |
+
"loss": 0.4275,
|
| 194 |
+
"step": 650
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.4,
|
| 198 |
+
"eval_loss": 0.4134916663169861,
|
| 199 |
+
"eval_runtime": 1.7005,
|
| 200 |
+
"eval_samples_per_second": 18.818,
|
| 201 |
+
"eval_steps_per_second": 9.409,
|
| 202 |
+
"eval_wer_score": 4.1200521966072206,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.43,
|
| 207 |
+
"learning_rate": 4.278052805280528e-05,
|
| 208 |
+
"loss": 0.4278,
|
| 209 |
+
"step": 700
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.43,
|
| 213 |
+
"eval_loss": 0.4126208424568176,
|
| 214 |
+
"eval_runtime": 2.7168,
|
| 215 |
+
"eval_samples_per_second": 11.779,
|
| 216 |
+
"eval_steps_per_second": 5.889,
|
| 217 |
+
"eval_wer_score": 4.035232709873858,
|
| 218 |
+
"step": 700
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.46,
|
| 222 |
+
"learning_rate": 4.226485148514852e-05,
|
| 223 |
+
"loss": 0.4251,
|
| 224 |
+
"step": 750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.46,
|
| 228 |
+
"eval_loss": 0.41297051310539246,
|
| 229 |
+
"eval_runtime": 2.3567,
|
| 230 |
+
"eval_samples_per_second": 13.578,
|
| 231 |
+
"eval_steps_per_second": 6.789,
|
| 232 |
+
"eval_wer_score": 4.082644628099174,
|
| 233 |
+
"step": 750
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5,
|
| 237 |
+
"learning_rate": 4.174917491749175e-05,
|
| 238 |
+
"loss": 0.4224,
|
| 239 |
+
"step": 800
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.5,
|
| 243 |
+
"eval_loss": 0.41018015146255493,
|
| 244 |
+
"eval_runtime": 1.6739,
|
| 245 |
+
"eval_samples_per_second": 19.117,
|
| 246 |
+
"eval_steps_per_second": 9.558,
|
| 247 |
+
"eval_wer_score": 4.034362766420183,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.53,
|
| 252 |
+
"learning_rate": 4.123349834983499e-05,
|
| 253 |
+
"loss": 0.4186,
|
| 254 |
+
"step": 850
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.53,
|
| 258 |
+
"eval_loss": 0.40729203820228577,
|
| 259 |
+
"eval_runtime": 3.0395,
|
| 260 |
+
"eval_samples_per_second": 10.528,
|
| 261 |
+
"eval_steps_per_second": 5.264,
|
| 262 |
+
"eval_wer_score": 4.054806437581557,
|
| 263 |
+
"step": 850
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.56,
|
| 267 |
+
"learning_rate": 4.071782178217822e-05,
|
| 268 |
+
"loss": 0.4186,
|
| 269 |
+
"step": 900
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.56,
|
| 273 |
+
"eval_loss": 0.4050724506378174,
|
| 274 |
+
"eval_runtime": 1.6968,
|
| 275 |
+
"eval_samples_per_second": 18.859,
|
| 276 |
+
"eval_steps_per_second": 9.429,
|
| 277 |
+
"eval_wer_score": 4.0669856459330145,
|
| 278 |
+
"step": 900
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.59,
|
| 282 |
+
"learning_rate": 4.020214521452145e-05,
|
| 283 |
+
"loss": 0.4159,
|
| 284 |
+
"step": 950
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.59,
|
| 288 |
+
"eval_loss": 0.4054299592971802,
|
| 289 |
+
"eval_runtime": 2.3306,
|
| 290 |
+
"eval_samples_per_second": 13.73,
|
| 291 |
+
"eval_steps_per_second": 6.865,
|
| 292 |
+
"eval_wer_score": 4.100043497172684,
|
| 293 |
+
"step": 950
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.62,
|
| 297 |
+
"learning_rate": 3.968646864686469e-05,
|
| 298 |
+
"loss": 0.4157,
|
| 299 |
+
"step": 1000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.62,
|
| 303 |
+
"eval_loss": 0.4036748707294464,
|
| 304 |
+
"eval_runtime": 2.3387,
|
| 305 |
+
"eval_samples_per_second": 13.683,
|
| 306 |
+
"eval_steps_per_second": 6.841,
|
| 307 |
+
"eval_wer_score": 4.08133971291866,
|
| 308 |
+
"step": 1000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.65,
|
| 312 |
+
"learning_rate": 3.917079207920793e-05,
|
| 313 |
+
"loss": 0.4141,
|
| 314 |
+
"step": 1050
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.65,
|
| 318 |
+
"eval_loss": 0.40399593114852905,
|
| 319 |
+
"eval_runtime": 1.6717,
|
| 320 |
+
"eval_samples_per_second": 19.142,
|
| 321 |
+
"eval_steps_per_second": 9.571,
|
| 322 |
+
"eval_wer_score": 4.090474119182253,
|
| 323 |
+
"step": 1050
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.68,
|
| 327 |
+
"learning_rate": 3.865511551155115e-05,
|
| 328 |
+
"loss": 0.4119,
|
| 329 |
+
"step": 1100
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.68,
|
| 333 |
+
"eval_loss": 0.4020461142063141,
|
| 334 |
+
"eval_runtime": 2.2547,
|
| 335 |
+
"eval_samples_per_second": 14.192,
|
| 336 |
+
"eval_steps_per_second": 7.096,
|
| 337 |
+
"eval_wer_score": 4.063505872118312,
|
| 338 |
+
"step": 1100
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.71,
|
| 342 |
+
"learning_rate": 3.813943894389439e-05,
|
| 343 |
+
"loss": 0.4104,
|
| 344 |
+
"step": 1150
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.71,
|
| 348 |
+
"eval_loss": 0.39923593401908875,
|
| 349 |
+
"eval_runtime": 2.3937,
|
| 350 |
+
"eval_samples_per_second": 13.368,
|
| 351 |
+
"eval_steps_per_second": 6.684,
|
| 352 |
+
"eval_wer_score": 4.0487168334058286,
|
| 353 |
+
"step": 1150
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.74,
|
| 357 |
+
"learning_rate": 3.762376237623763e-05,
|
| 358 |
+
"loss": 0.4104,
|
| 359 |
+
"step": 1200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.74,
|
| 363 |
+
"eval_loss": 0.39828553795814514,
|
| 364 |
+
"eval_runtime": 1.6946,
|
| 365 |
+
"eval_samples_per_second": 18.883,
|
| 366 |
+
"eval_steps_per_second": 9.442,
|
| 367 |
+
"eval_wer_score": 4.107438016528926,
|
| 368 |
+
"step": 1200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.77,
|
| 372 |
+
"learning_rate": 3.710808580858086e-05,
|
| 373 |
+
"loss": 0.4086,
|
| 374 |
+
"step": 1250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.77,
|
| 378 |
+
"eval_loss": 0.3990360200405121,
|
| 379 |
+
"eval_runtime": 2.3013,
|
| 380 |
+
"eval_samples_per_second": 13.905,
|
| 381 |
+
"eval_steps_per_second": 6.953,
|
| 382 |
+
"eval_wer_score": 4.1022183558068726,
|
| 383 |
+
"step": 1250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.8,
|
| 387 |
+
"learning_rate": 3.659240924092409e-05,
|
| 388 |
+
"loss": 0.4082,
|
| 389 |
+
"step": 1300
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.8,
|
| 393 |
+
"eval_loss": 0.39795249700546265,
|
| 394 |
+
"eval_runtime": 2.3895,
|
| 395 |
+
"eval_samples_per_second": 13.392,
|
| 396 |
+
"eval_steps_per_second": 6.696,
|
| 397 |
+
"eval_wer_score": 4.086124401913875,
|
| 398 |
+
"step": 1300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.84,
|
| 402 |
+
"learning_rate": 3.607673267326733e-05,
|
| 403 |
+
"loss": 0.4071,
|
| 404 |
+
"step": 1350
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.84,
|
| 408 |
+
"eval_loss": 0.39599987864494324,
|
| 409 |
+
"eval_runtime": 1.6611,
|
| 410 |
+
"eval_samples_per_second": 19.265,
|
| 411 |
+
"eval_steps_per_second": 9.632,
|
| 412 |
+
"eval_wer_score": 4.075250108742932,
|
| 413 |
+
"step": 1350
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.87,
|
| 417 |
+
"learning_rate": 3.556105610561056e-05,
|
| 418 |
+
"loss": 0.4057,
|
| 419 |
+
"step": 1400
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.87,
|
| 423 |
+
"eval_loss": 0.39804807305336,
|
| 424 |
+
"eval_runtime": 2.3409,
|
| 425 |
+
"eval_samples_per_second": 13.67,
|
| 426 |
+
"eval_steps_per_second": 6.835,
|
| 427 |
+
"eval_wer_score": 4.056546324488909,
|
| 428 |
+
"step": 1400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.9,
|
| 432 |
+
"learning_rate": 3.50453795379538e-05,
|
| 433 |
+
"loss": 0.4067,
|
| 434 |
+
"step": 1450
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9,
|
| 438 |
+
"eval_loss": 0.3962915241718292,
|
| 439 |
+
"eval_runtime": 2.295,
|
| 440 |
+
"eval_samples_per_second": 13.944,
|
| 441 |
+
"eval_steps_per_second": 6.972,
|
| 442 |
+
"eval_wer_score": 4.103088299260548,
|
| 443 |
+
"step": 1450
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.93,
|
| 447 |
+
"learning_rate": 3.452970297029703e-05,
|
| 448 |
+
"loss": 0.404,
|
| 449 |
+
"step": 1500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.93,
|
| 453 |
+
"eval_loss": 0.3967008888721466,
|
| 454 |
+
"eval_runtime": 2.3182,
|
| 455 |
+
"eval_samples_per_second": 13.804,
|
| 456 |
+
"eval_steps_per_second": 6.902,
|
| 457 |
+
"eval_wer_score": 4.110047846889952,
|
| 458 |
+
"step": 1500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.96,
|
| 462 |
+
"learning_rate": 3.4014026402640264e-05,
|
| 463 |
+
"loss": 0.4019,
|
| 464 |
+
"step": 1550
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.96,
|
| 468 |
+
"eval_loss": 0.39423680305480957,
|
| 469 |
+
"eval_runtime": 2.2298,
|
| 470 |
+
"eval_samples_per_second": 14.351,
|
| 471 |
+
"eval_steps_per_second": 7.176,
|
| 472 |
+
"eval_wer_score": 4.082644628099174,
|
| 473 |
+
"step": 1550
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.99,
|
| 477 |
+
"learning_rate": 3.34983498349835e-05,
|
| 478 |
+
"loss": 0.4002,
|
| 479 |
+
"step": 1600
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.99,
|
| 483 |
+
"eval_loss": 0.39309296011924744,
|
| 484 |
+
"eval_runtime": 2.3184,
|
| 485 |
+
"eval_samples_per_second": 13.803,
|
| 486 |
+
"eval_steps_per_second": 6.901,
|
| 487 |
+
"eval_wer_score": 4.07742496737712,
|
| 488 |
+
"step": 1600
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.02,
|
| 492 |
+
"learning_rate": 3.2982673267326734e-05,
|
| 493 |
+
"loss": 0.3975,
|
| 494 |
+
"step": 1650
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.02,
|
| 498 |
+
"eval_loss": 0.39335134625434875,
|
| 499 |
+
"eval_runtime": 2.2755,
|
| 500 |
+
"eval_samples_per_second": 14.063,
|
| 501 |
+
"eval_steps_per_second": 7.032,
|
| 502 |
+
"eval_wer_score": 4.10656807307525,
|
| 503 |
+
"step": 1650
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.05,
|
| 507 |
+
"learning_rate": 3.2466996699669965e-05,
|
| 508 |
+
"loss": 0.3932,
|
| 509 |
+
"step": 1700
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.05,
|
| 513 |
+
"eval_loss": 0.3922082781791687,
|
| 514 |
+
"eval_runtime": 2.3564,
|
| 515 |
+
"eval_samples_per_second": 13.58,
|
| 516 |
+
"eval_steps_per_second": 6.79,
|
| 517 |
+
"eval_wer_score": 4.048281861678991,
|
| 518 |
+
"step": 1700
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.08,
|
| 522 |
+
"learning_rate": 3.1951320132013203e-05,
|
| 523 |
+
"loss": 0.3922,
|
| 524 |
+
"step": 1750
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.08,
|
| 528 |
+
"eval_loss": 0.392187237739563,
|
| 529 |
+
"eval_runtime": 2.3537,
|
| 530 |
+
"eval_samples_per_second": 13.596,
|
| 531 |
+
"eval_steps_per_second": 6.798,
|
| 532 |
+
"eval_wer_score": 4.079164854284471,
|
| 533 |
+
"step": 1750
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.11,
|
| 537 |
+
"learning_rate": 3.1435643564356435e-05,
|
| 538 |
+
"loss": 0.3929,
|
| 539 |
+
"step": 1800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.11,
|
| 543 |
+
"eval_loss": 0.39260441064834595,
|
| 544 |
+
"eval_runtime": 2.3232,
|
| 545 |
+
"eval_samples_per_second": 13.774,
|
| 546 |
+
"eval_steps_per_second": 6.887,
|
| 547 |
+
"eval_wer_score": 4.020443671161375,
|
| 548 |
+
"step": 1800
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.14,
|
| 552 |
+
"learning_rate": 3.0919966996699673e-05,
|
| 553 |
+
"loss": 0.3914,
|
| 554 |
+
"step": 1850
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.14,
|
| 558 |
+
"eval_loss": 0.3927755355834961,
|
| 559 |
+
"eval_runtime": 2.2418,
|
| 560 |
+
"eval_samples_per_second": 14.274,
|
| 561 |
+
"eval_steps_per_second": 7.137,
|
| 562 |
+
"eval_wer_score": 4.090474119182253,
|
| 563 |
+
"step": 1850
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.18,
|
| 567 |
+
"learning_rate": 3.0404290429042902e-05,
|
| 568 |
+
"loss": 0.3911,
|
| 569 |
+
"step": 1900
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.18,
|
| 573 |
+
"eval_loss": 0.39090630412101746,
|
| 574 |
+
"eval_runtime": 2.3278,
|
| 575 |
+
"eval_samples_per_second": 13.747,
|
| 576 |
+
"eval_steps_per_second": 6.873,
|
| 577 |
+
"eval_wer_score": 4.040887342322749,
|
| 578 |
+
"step": 1900
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.21,
|
| 582 |
+
"learning_rate": 2.988861386138614e-05,
|
| 583 |
+
"loss": 0.3903,
|
| 584 |
+
"step": 1950
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.21,
|
| 588 |
+
"eval_loss": 0.3916274607181549,
|
| 589 |
+
"eval_runtime": 2.2878,
|
| 590 |
+
"eval_samples_per_second": 13.987,
|
| 591 |
+
"eval_steps_per_second": 6.994,
|
| 592 |
+
"eval_wer_score": 4.0426272292301,
|
| 593 |
+
"step": 1950
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.24,
|
| 597 |
+
"learning_rate": 2.9372937293729375e-05,
|
| 598 |
+
"loss": 0.3906,
|
| 599 |
+
"step": 2000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.24,
|
| 603 |
+
"eval_loss": 0.39041662216186523,
|
| 604 |
+
"eval_runtime": 2.3191,
|
| 605 |
+
"eval_samples_per_second": 13.798,
|
| 606 |
+
"eval_steps_per_second": 6.899,
|
| 607 |
+
"eval_wer_score": 4.063505872118312,
|
| 608 |
+
"step": 2000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.27,
|
| 612 |
+
"learning_rate": 2.885726072607261e-05,
|
| 613 |
+
"loss": 0.3887,
|
| 614 |
+
"step": 2050
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.27,
|
| 618 |
+
"eval_loss": 0.39140254259109497,
|
| 619 |
+
"eval_runtime": 2.3005,
|
| 620 |
+
"eval_samples_per_second": 13.91,
|
| 621 |
+
"eval_steps_per_second": 6.955,
|
| 622 |
+
"eval_wer_score": 4.08133971291866,
|
| 623 |
+
"step": 2050
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.3,
|
| 627 |
+
"learning_rate": 2.834158415841584e-05,
|
| 628 |
+
"loss": 0.3899,
|
| 629 |
+
"step": 2100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.3,
|
| 633 |
+
"eval_loss": 0.39112603664398193,
|
| 634 |
+
"eval_runtime": 2.3634,
|
| 635 |
+
"eval_samples_per_second": 13.54,
|
| 636 |
+
"eval_steps_per_second": 6.77,
|
| 637 |
+
"eval_wer_score": 4.0491518051326665,
|
| 638 |
+
"step": 2100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.33,
|
| 642 |
+
"learning_rate": 2.7825907590759077e-05,
|
| 643 |
+
"loss": 0.389,
|
| 644 |
+
"step": 2150
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.33,
|
| 648 |
+
"eval_loss": 0.3917953073978424,
|
| 649 |
+
"eval_runtime": 2.2409,
|
| 650 |
+
"eval_samples_per_second": 14.28,
|
| 651 |
+
"eval_steps_per_second": 7.14,
|
| 652 |
+
"eval_wer_score": 4.098738581992171,
|
| 653 |
+
"step": 2150
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.36,
|
| 657 |
+
"learning_rate": 2.731023102310231e-05,
|
| 658 |
+
"loss": 0.3878,
|
| 659 |
+
"step": 2200
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.36,
|
| 663 |
+
"eval_loss": 0.38973185420036316,
|
| 664 |
+
"eval_runtime": 2.3148,
|
| 665 |
+
"eval_samples_per_second": 13.824,
|
| 666 |
+
"eval_steps_per_second": 6.912,
|
| 667 |
+
"eval_wer_score": 4.091779034362767,
|
| 668 |
+
"step": 2200
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.39,
|
| 672 |
+
"learning_rate": 2.6794554455445547e-05,
|
| 673 |
+
"loss": 0.3877,
|
| 674 |
+
"step": 2250
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.39,
|
| 678 |
+
"eval_loss": 0.387917160987854,
|
| 679 |
+
"eval_runtime": 2.3247,
|
| 680 |
+
"eval_samples_per_second": 13.765,
|
| 681 |
+
"eval_steps_per_second": 6.883,
|
| 682 |
+
"eval_wer_score": 4.068290561113527,
|
| 683 |
+
"step": 2250
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.42,
|
| 687 |
+
"learning_rate": 2.6278877887788778e-05,
|
| 688 |
+
"loss": 0.3871,
|
| 689 |
+
"step": 2300
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.42,
|
| 693 |
+
"eval_loss": 0.3881215453147888,
|
| 694 |
+
"eval_runtime": 2.2878,
|
| 695 |
+
"eval_samples_per_second": 13.987,
|
| 696 |
+
"eval_steps_per_second": 6.994,
|
| 697 |
+
"eval_wer_score": 4.076989995650282,
|
| 698 |
+
"step": 2300
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.45,
|
| 702 |
+
"learning_rate": 2.5763201320132013e-05,
|
| 703 |
+
"loss": 0.387,
|
| 704 |
+
"step": 2350
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.45,
|
| 708 |
+
"eval_loss": 0.3859871029853821,
|
| 709 |
+
"eval_runtime": 2.3063,
|
| 710 |
+
"eval_samples_per_second": 13.875,
|
| 711 |
+
"eval_steps_per_second": 6.937,
|
| 712 |
+
"eval_wer_score": 4.069160504567203,
|
| 713 |
+
"step": 2350
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.49,
|
| 717 |
+
"learning_rate": 2.5247524752475248e-05,
|
| 718 |
+
"loss": 0.3887,
|
| 719 |
+
"step": 2400
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.49,
|
| 723 |
+
"eval_loss": 0.38679689168930054,
|
| 724 |
+
"eval_runtime": 2.3448,
|
| 725 |
+
"eval_samples_per_second": 13.647,
|
| 726 |
+
"eval_steps_per_second": 6.824,
|
| 727 |
+
"eval_wer_score": 4.063070900391475,
|
| 728 |
+
"step": 2400
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.52,
|
| 732 |
+
"learning_rate": 2.4731848184818483e-05,
|
| 733 |
+
"loss": 0.3847,
|
| 734 |
+
"step": 2450
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.52,
|
| 738 |
+
"eval_loss": 0.3876645267009735,
|
| 739 |
+
"eval_runtime": 1.6183,
|
| 740 |
+
"eval_samples_per_second": 19.774,
|
| 741 |
+
"eval_steps_per_second": 9.887,
|
| 742 |
+
"eval_wer_score": 4.091344062635929,
|
| 743 |
+
"step": 2450
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.55,
|
| 747 |
+
"learning_rate": 2.4216171617161718e-05,
|
| 748 |
+
"loss": 0.3854,
|
| 749 |
+
"step": 2500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.55,
|
| 753 |
+
"eval_loss": 0.3880044221878052,
|
| 754 |
+
"eval_runtime": 1.6125,
|
| 755 |
+
"eval_samples_per_second": 19.845,
|
| 756 |
+
"eval_steps_per_second": 9.923,
|
| 757 |
+
"eval_wer_score": 4.040887342322749,
|
| 758 |
+
"step": 2500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.58,
|
| 762 |
+
"learning_rate": 2.370049504950495e-05,
|
| 763 |
+
"loss": 0.3841,
|
| 764 |
+
"step": 2550
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.58,
|
| 768 |
+
"eval_loss": 0.38710057735443115,
|
| 769 |
+
"eval_runtime": 1.6138,
|
| 770 |
+
"eval_samples_per_second": 19.829,
|
| 771 |
+
"eval_steps_per_second": 9.914,
|
| 772 |
+
"eval_wer_score": 4.064810787298826,
|
| 773 |
+
"step": 2550
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.61,
|
| 777 |
+
"learning_rate": 2.3184818481848185e-05,
|
| 778 |
+
"loss": 0.384,
|
| 779 |
+
"step": 2600
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.61,
|
| 783 |
+
"eval_loss": 0.3867349326610565,
|
| 784 |
+
"eval_runtime": 1.6339,
|
| 785 |
+
"eval_samples_per_second": 19.585,
|
| 786 |
+
"eval_steps_per_second": 9.793,
|
| 787 |
+
"eval_wer_score": 4.063070900391475,
|
| 788 |
+
"step": 2600
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.64,
|
| 792 |
+
"learning_rate": 2.266914191419142e-05,
|
| 793 |
+
"loss": 0.3839,
|
| 794 |
+
"step": 2650
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.64,
|
| 798 |
+
"eval_loss": 0.38524535298347473,
|
| 799 |
+
"eval_runtime": 1.6377,
|
| 800 |
+
"eval_samples_per_second": 19.539,
|
| 801 |
+
"eval_steps_per_second": 9.77,
|
| 802 |
+
"eval_wer_score": 4.076989995650282,
|
| 803 |
+
"step": 2650
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.67,
|
| 807 |
+
"learning_rate": 2.2153465346534655e-05,
|
| 808 |
+
"loss": 0.3833,
|
| 809 |
+
"step": 2700
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.67,
|
| 813 |
+
"eval_loss": 0.3858553171157837,
|
| 814 |
+
"eval_runtime": 1.6388,
|
| 815 |
+
"eval_samples_per_second": 19.526,
|
| 816 |
+
"eval_steps_per_second": 9.763,
|
| 817 |
+
"eval_wer_score": 4.033492822966507,
|
| 818 |
+
"step": 2700
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.7,
|
| 822 |
+
"learning_rate": 2.1637788778877886e-05,
|
| 823 |
+
"loss": 0.3819,
|
| 824 |
+
"step": 2750
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.7,
|
| 828 |
+
"eval_loss": 0.38464829325675964,
|
| 829 |
+
"eval_runtime": 1.6686,
|
| 830 |
+
"eval_samples_per_second": 19.178,
|
| 831 |
+
"eval_steps_per_second": 9.589,
|
| 832 |
+
"eval_wer_score": 4.073510221835581,
|
| 833 |
+
"step": 2750
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.73,
|
| 837 |
+
"learning_rate": 2.1122112211221125e-05,
|
| 838 |
+
"loss": 0.3831,
|
| 839 |
+
"step": 2800
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.73,
|
| 843 |
+
"eval_loss": 0.3838270902633667,
|
| 844 |
+
"eval_runtime": 1.6915,
|
| 845 |
+
"eval_samples_per_second": 18.918,
|
| 846 |
+
"eval_steps_per_second": 9.459,
|
| 847 |
+
"eval_wer_score": 4.0678555893866895,
|
| 848 |
+
"step": 2800
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.76,
|
| 852 |
+
"learning_rate": 2.0606435643564356e-05,
|
| 853 |
+
"loss": 0.3817,
|
| 854 |
+
"step": 2850
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.76,
|
| 858 |
+
"eval_loss": 0.38364166021347046,
|
| 859 |
+
"eval_runtime": 1.6576,
|
| 860 |
+
"eval_samples_per_second": 19.305,
|
| 861 |
+
"eval_steps_per_second": 9.653,
|
| 862 |
+
"eval_wer_score": 4.051761635493693,
|
| 863 |
+
"step": 2850
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.79,
|
| 867 |
+
"learning_rate": 2.009075907590759e-05,
|
| 868 |
+
"loss": 0.3811,
|
| 869 |
+
"step": 2900
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.79,
|
| 873 |
+
"eval_loss": 0.38430899381637573,
|
| 874 |
+
"eval_runtime": 1.6858,
|
| 875 |
+
"eval_samples_per_second": 18.982,
|
| 876 |
+
"eval_steps_per_second": 9.491,
|
| 877 |
+
"eval_wer_score": 4.053936494127882,
|
| 878 |
+
"step": 2900
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.83,
|
| 882 |
+
"learning_rate": 1.9575082508250826e-05,
|
| 883 |
+
"loss": 0.3821,
|
| 884 |
+
"step": 2950
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.83,
|
| 888 |
+
"eval_loss": 0.3839759826660156,
|
| 889 |
+
"eval_runtime": 1.6393,
|
| 890 |
+
"eval_samples_per_second": 19.52,
|
| 891 |
+
"eval_steps_per_second": 9.76,
|
| 892 |
+
"eval_wer_score": 4.08133971291866,
|
| 893 |
+
"step": 2950
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.86,
|
| 897 |
+
"learning_rate": 1.905940594059406e-05,
|
| 898 |
+
"loss": 0.3803,
|
| 899 |
+
"step": 3000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.86,
|
| 903 |
+
"eval_loss": 0.3829007148742676,
|
| 904 |
+
"eval_runtime": 1.757,
|
| 905 |
+
"eval_samples_per_second": 18.212,
|
| 906 |
+
"eval_steps_per_second": 9.106,
|
| 907 |
+
"eval_wer_score": 4.043932144410613,
|
| 908 |
+
"step": 3000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.89,
|
| 912 |
+
"learning_rate": 1.8543729372937293e-05,
|
| 913 |
+
"loss": 0.3804,
|
| 914 |
+
"step": 3050
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.89,
|
| 918 |
+
"eval_loss": 0.3814784288406372,
|
| 919 |
+
"eval_runtime": 1.7626,
|
| 920 |
+
"eval_samples_per_second": 18.155,
|
| 921 |
+
"eval_steps_per_second": 9.078,
|
| 922 |
+
"eval_wer_score": 4.068725532840365,
|
| 923 |
+
"step": 3050
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.92,
|
| 927 |
+
"learning_rate": 1.8028052805280528e-05,
|
| 928 |
+
"loss": 0.3803,
|
| 929 |
+
"step": 3100
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.92,
|
| 933 |
+
"eval_loss": 0.382568895816803,
|
| 934 |
+
"eval_runtime": 1.7262,
|
| 935 |
+
"eval_samples_per_second": 18.538,
|
| 936 |
+
"eval_steps_per_second": 9.269,
|
| 937 |
+
"eval_wer_score": 4.033927794693345,
|
| 938 |
+
"step": 3100
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.95,
|
| 942 |
+
"learning_rate": 1.7512376237623763e-05,
|
| 943 |
+
"loss": 0.3774,
|
| 944 |
+
"step": 3150
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.95,
|
| 948 |
+
"eval_loss": 0.38378775119781494,
|
| 949 |
+
"eval_runtime": 1.776,
|
| 950 |
+
"eval_samples_per_second": 18.018,
|
| 951 |
+
"eval_steps_per_second": 9.009,
|
| 952 |
+
"eval_wer_score": 4.053936494127882,
|
| 953 |
+
"step": 3150
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.98,
|
| 957 |
+
"learning_rate": 1.6996699669966998e-05,
|
| 958 |
+
"loss": 0.379,
|
| 959 |
+
"step": 3200
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.98,
|
| 963 |
+
"eval_loss": 0.3831249475479126,
|
| 964 |
+
"eval_runtime": 1.7324,
|
| 965 |
+
"eval_samples_per_second": 18.471,
|
| 966 |
+
"eval_steps_per_second": 9.236,
|
| 967 |
+
"eval_wer_score": 4.062635928664637,
|
| 968 |
+
"step": 3200
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.01,
|
| 972 |
+
"learning_rate": 1.648102310231023e-05,
|
| 973 |
+
"loss": 0.3779,
|
| 974 |
+
"step": 3250
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.01,
|
| 978 |
+
"eval_loss": 0.3829612135887146,
|
| 979 |
+
"eval_runtime": 1.7483,
|
| 980 |
+
"eval_samples_per_second": 18.304,
|
| 981 |
+
"eval_steps_per_second": 9.152,
|
| 982 |
+
"eval_wer_score": 4.070465419747716,
|
| 983 |
+
"step": 3250
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.04,
|
| 987 |
+
"learning_rate": 1.5965346534653468e-05,
|
| 988 |
+
"loss": 0.3714,
|
| 989 |
+
"step": 3300
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.04,
|
| 993 |
+
"eval_loss": 0.38411805033683777,
|
| 994 |
+
"eval_runtime": 1.7491,
|
| 995 |
+
"eval_samples_per_second": 18.295,
|
| 996 |
+
"eval_steps_per_second": 9.147,
|
| 997 |
+
"eval_wer_score": 4.074380165289257,
|
| 998 |
+
"step": 3300
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.07,
|
| 1002 |
+
"learning_rate": 1.54496699669967e-05,
|
| 1003 |
+
"loss": 0.3718,
|
| 1004 |
+
"step": 3350
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.07,
|
| 1008 |
+
"eval_loss": 0.38236159086227417,
|
| 1009 |
+
"eval_runtime": 1.7284,
|
| 1010 |
+
"eval_samples_per_second": 18.514,
|
| 1011 |
+
"eval_steps_per_second": 9.257,
|
| 1012 |
+
"eval_wer_score": 4.076555023923445,
|
| 1013 |
+
"step": 3350
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.1,
|
| 1017 |
+
"learning_rate": 1.4933993399339935e-05,
|
| 1018 |
+
"loss": 0.3705,
|
| 1019 |
+
"step": 3400
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.1,
|
| 1023 |
+
"eval_loss": 0.3845175504684448,
|
| 1024 |
+
"eval_runtime": 1.748,
|
| 1025 |
+
"eval_samples_per_second": 18.307,
|
| 1026 |
+
"eval_steps_per_second": 9.153,
|
| 1027 |
+
"eval_wer_score": 4.075250108742932,
|
| 1028 |
+
"step": 3400
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.13,
|
| 1032 |
+
"learning_rate": 1.4418316831683168e-05,
|
| 1033 |
+
"loss": 0.3719,
|
| 1034 |
+
"step": 3450
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.13,
|
| 1038 |
+
"eval_loss": 0.382493793964386,
|
| 1039 |
+
"eval_runtime": 1.7164,
|
| 1040 |
+
"eval_samples_per_second": 18.643,
|
| 1041 |
+
"eval_steps_per_second": 9.322,
|
| 1042 |
+
"eval_wer_score": 4.0848194867333625,
|
| 1043 |
+
"step": 3450
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.17,
|
| 1047 |
+
"learning_rate": 1.3902640264026403e-05,
|
| 1048 |
+
"loss": 0.3715,
|
| 1049 |
+
"step": 3500
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.17,
|
| 1053 |
+
"eval_loss": 0.3831576108932495,
|
| 1054 |
+
"eval_runtime": 1.7528,
|
| 1055 |
+
"eval_samples_per_second": 18.257,
|
| 1056 |
+
"eval_steps_per_second": 9.128,
|
| 1057 |
+
"eval_wer_score": 4.061765985210961,
|
| 1058 |
+
"step": 3500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.2,
|
| 1062 |
+
"learning_rate": 1.3386963696369636e-05,
|
| 1063 |
+
"loss": 0.3704,
|
| 1064 |
+
"step": 3550
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 2.2,
|
| 1068 |
+
"eval_loss": 0.38182923197746277,
|
| 1069 |
+
"eval_runtime": 1.8646,
|
| 1070 |
+
"eval_samples_per_second": 17.161,
|
| 1071 |
+
"eval_steps_per_second": 8.581,
|
| 1072 |
+
"eval_wer_score": 4.0843845150065246,
|
| 1073 |
+
"step": 3550
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.23,
|
| 1077 |
+
"learning_rate": 1.2871287128712873e-05,
|
| 1078 |
+
"loss": 0.3703,
|
| 1079 |
+
"step": 3600
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.23,
|
| 1083 |
+
"eval_loss": 0.38130998611450195,
|
| 1084 |
+
"eval_runtime": 1.7229,
|
| 1085 |
+
"eval_samples_per_second": 18.574,
|
| 1086 |
+
"eval_steps_per_second": 9.287,
|
| 1087 |
+
"eval_wer_score": 4.063070900391475,
|
| 1088 |
+
"step": 3600
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.26,
|
| 1092 |
+
"learning_rate": 1.2355610561056106e-05,
|
| 1093 |
+
"loss": 0.3697,
|
| 1094 |
+
"step": 3650
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.26,
|
| 1098 |
+
"eval_loss": 0.381599485874176,
|
| 1099 |
+
"eval_runtime": 1.7655,
|
| 1100 |
+
"eval_samples_per_second": 18.126,
|
| 1101 |
+
"eval_steps_per_second": 9.063,
|
| 1102 |
+
"eval_wer_score": 4.073510221835581,
|
| 1103 |
+
"step": 3650
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.29,
|
| 1107 |
+
"learning_rate": 1.1839933993399341e-05,
|
| 1108 |
+
"loss": 0.3706,
|
| 1109 |
+
"step": 3700
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.29,
|
| 1113 |
+
"eval_loss": 0.3811095952987671,
|
| 1114 |
+
"eval_runtime": 1.7447,
|
| 1115 |
+
"eval_samples_per_second": 18.341,
|
| 1116 |
+
"eval_steps_per_second": 9.171,
|
| 1117 |
+
"eval_wer_score": 4.06394084384515,
|
| 1118 |
+
"step": 3700
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.32,
|
| 1122 |
+
"learning_rate": 1.1324257425742574e-05,
|
| 1123 |
+
"loss": 0.3709,
|
| 1124 |
+
"step": 3750
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.32,
|
| 1128 |
+
"eval_loss": 0.3830665946006775,
|
| 1129 |
+
"eval_runtime": 1.7245,
|
| 1130 |
+
"eval_samples_per_second": 18.556,
|
| 1131 |
+
"eval_steps_per_second": 9.278,
|
| 1132 |
+
"eval_wer_score": 4.070900391474554,
|
| 1133 |
+
"step": 3750
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.35,
|
| 1137 |
+
"learning_rate": 1.080858085808581e-05,
|
| 1138 |
+
"loss": 0.3698,
|
| 1139 |
+
"step": 3800
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.35,
|
| 1143 |
+
"eval_loss": 0.38286030292510986,
|
| 1144 |
+
"eval_runtime": 1.7434,
|
| 1145 |
+
"eval_samples_per_second": 18.355,
|
| 1146 |
+
"eval_steps_per_second": 9.178,
|
| 1147 |
+
"eval_wer_score": 4.066115702479339,
|
| 1148 |
+
"step": 3800
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.38,
|
| 1152 |
+
"learning_rate": 1.0292904290429044e-05,
|
| 1153 |
+
"loss": 0.3692,
|
| 1154 |
+
"step": 3850
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.38,
|
| 1158 |
+
"eval_loss": 0.38252702355384827,
|
| 1159 |
+
"eval_runtime": 1.7413,
|
| 1160 |
+
"eval_samples_per_second": 18.377,
|
| 1161 |
+
"eval_steps_per_second": 9.189,
|
| 1162 |
+
"eval_wer_score": 4.063070900391475,
|
| 1163 |
+
"step": 3850
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 2.41,
|
| 1167 |
+
"learning_rate": 9.777227722772278e-06,
|
| 1168 |
+
"loss": 0.3695,
|
| 1169 |
+
"step": 3900
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.41,
|
| 1173 |
+
"eval_loss": 0.3817928731441498,
|
| 1174 |
+
"eval_runtime": 1.7445,
|
| 1175 |
+
"eval_samples_per_second": 18.343,
|
| 1176 |
+
"eval_steps_per_second": 9.172,
|
| 1177 |
+
"eval_wer_score": 4.0665506742061766,
|
| 1178 |
+
"step": 3900
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.44,
|
| 1182 |
+
"learning_rate": 9.261551155115513e-06,
|
| 1183 |
+
"loss": 0.3678,
|
| 1184 |
+
"step": 3950
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.44,
|
| 1188 |
+
"eval_loss": 0.38285502791404724,
|
| 1189 |
+
"eval_runtime": 1.7607,
|
| 1190 |
+
"eval_samples_per_second": 18.174,
|
| 1191 |
+
"eval_steps_per_second": 9.087,
|
| 1192 |
+
"eval_wer_score": 4.053936494127882,
|
| 1193 |
+
"step": 3950
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.48,
|
| 1197 |
+
"learning_rate": 8.745874587458746e-06,
|
| 1198 |
+
"loss": 0.3679,
|
| 1199 |
+
"step": 4000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.48,
|
| 1203 |
+
"eval_loss": 0.38176512718200684,
|
| 1204 |
+
"eval_runtime": 1.731,
|
| 1205 |
+
"eval_samples_per_second": 18.487,
|
| 1206 |
+
"eval_steps_per_second": 9.243,
|
| 1207 |
+
"eval_wer_score": 4.0939538929969554,
|
| 1208 |
+
"step": 4000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.51,
|
| 1212 |
+
"learning_rate": 8.230198019801981e-06,
|
| 1213 |
+
"loss": 0.3692,
|
| 1214 |
+
"step": 4050
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.51,
|
| 1218 |
+
"eval_loss": 0.3833461403846741,
|
| 1219 |
+
"eval_runtime": 1.7399,
|
| 1220 |
+
"eval_samples_per_second": 18.392,
|
| 1221 |
+
"eval_steps_per_second": 9.196,
|
| 1222 |
+
"eval_wer_score": 4.0856894301870375,
|
| 1223 |
+
"step": 4050
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.54,
|
| 1227 |
+
"learning_rate": 7.714521452145216e-06,
|
| 1228 |
+
"loss": 0.3691,
|
| 1229 |
+
"step": 4100
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.54,
|
| 1233 |
+
"eval_loss": 0.381513774394989,
|
| 1234 |
+
"eval_runtime": 1.7336,
|
| 1235 |
+
"eval_samples_per_second": 18.458,
|
| 1236 |
+
"eval_steps_per_second": 9.229,
|
| 1237 |
+
"eval_wer_score": 4.061765985210961,
|
| 1238 |
+
"step": 4100
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.57,
|
| 1242 |
+
"learning_rate": 7.198844884488449e-06,
|
| 1243 |
+
"loss": 0.3674,
|
| 1244 |
+
"step": 4150
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.57,
|
| 1248 |
+
"eval_loss": 0.38187551498413086,
|
| 1249 |
+
"eval_runtime": 1.7502,
|
| 1250 |
+
"eval_samples_per_second": 18.284,
|
| 1251 |
+
"eval_steps_per_second": 9.142,
|
| 1252 |
+
"eval_wer_score": 4.069595476294041,
|
| 1253 |
+
"step": 4150
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 2.6,
|
| 1257 |
+
"learning_rate": 6.6831683168316835e-06,
|
| 1258 |
+
"loss": 0.3675,
|
| 1259 |
+
"step": 4200
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.6,
|
| 1263 |
+
"eval_loss": 0.38118019700050354,
|
| 1264 |
+
"eval_runtime": 1.7491,
|
| 1265 |
+
"eval_samples_per_second": 18.295,
|
| 1266 |
+
"eval_steps_per_second": 9.147,
|
| 1267 |
+
"eval_wer_score": 4.0491518051326665,
|
| 1268 |
+
"step": 4200
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 2.63,
|
| 1272 |
+
"learning_rate": 6.167491749174918e-06,
|
| 1273 |
+
"loss": 0.3683,
|
| 1274 |
+
"step": 4250
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.63,
|
| 1278 |
+
"eval_loss": 0.38107800483703613,
|
| 1279 |
+
"eval_runtime": 1.7521,
|
| 1280 |
+
"eval_samples_per_second": 18.264,
|
| 1281 |
+
"eval_steps_per_second": 9.132,
|
| 1282 |
+
"eval_wer_score": 4.057416267942584,
|
| 1283 |
+
"step": 4250
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.66,
|
| 1287 |
+
"learning_rate": 5.651815181518152e-06,
|
| 1288 |
+
"loss": 0.3688,
|
| 1289 |
+
"step": 4300
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.66,
|
| 1293 |
+
"eval_loss": 0.3809460401535034,
|
| 1294 |
+
"eval_runtime": 1.7731,
|
| 1295 |
+
"eval_samples_per_second": 18.047,
|
| 1296 |
+
"eval_steps_per_second": 9.024,
|
| 1297 |
+
"eval_wer_score": 4.06002609830361,
|
| 1298 |
+
"step": 4300
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.69,
|
| 1302 |
+
"learning_rate": 5.136138613861386e-06,
|
| 1303 |
+
"loss": 0.3661,
|
| 1304 |
+
"step": 4350
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.69,
|
| 1308 |
+
"eval_loss": 0.3806704878807068,
|
| 1309 |
+
"eval_runtime": 1.7466,
|
| 1310 |
+
"eval_samples_per_second": 18.321,
|
| 1311 |
+
"eval_steps_per_second": 9.16,
|
| 1312 |
+
"eval_wer_score": 4.070030448020878,
|
| 1313 |
+
"step": 4350
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.72,
|
| 1317 |
+
"learning_rate": 4.62046204620462e-06,
|
| 1318 |
+
"loss": 0.3685,
|
| 1319 |
+
"step": 4400
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.72,
|
| 1323 |
+
"eval_loss": 0.3806542456150055,
|
| 1324 |
+
"eval_runtime": 1.7323,
|
| 1325 |
+
"eval_samples_per_second": 18.473,
|
| 1326 |
+
"eval_steps_per_second": 9.236,
|
| 1327 |
+
"eval_wer_score": 4.0400173988690735,
|
| 1328 |
+
"step": 4400
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 2.75,
|
| 1332 |
+
"learning_rate": 4.104785478547855e-06,
|
| 1333 |
+
"loss": 0.3665,
|
| 1334 |
+
"step": 4450
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.75,
|
| 1338 |
+
"eval_loss": 0.3803941607475281,
|
| 1339 |
+
"eval_runtime": 1.8056,
|
| 1340 |
+
"eval_samples_per_second": 17.723,
|
| 1341 |
+
"eval_steps_per_second": 8.861,
|
| 1342 |
+
"eval_wer_score": 4.07177033492823,
|
| 1343 |
+
"step": 4450
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.78,
|
| 1347 |
+
"learning_rate": 3.589108910891089e-06,
|
| 1348 |
+
"loss": 0.3665,
|
| 1349 |
+
"step": 4500
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.78,
|
| 1353 |
+
"eval_loss": 0.38016611337661743,
|
| 1354 |
+
"eval_runtime": 1.7258,
|
| 1355 |
+
"eval_samples_per_second": 18.542,
|
| 1356 |
+
"eval_steps_per_second": 9.271,
|
| 1357 |
+
"eval_wer_score": 4.04654197477164,
|
| 1358 |
+
"step": 4500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 2.82,
|
| 1362 |
+
"learning_rate": 3.073432343234324e-06,
|
| 1363 |
+
"loss": 0.3651,
|
| 1364 |
+
"step": 4550
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 2.82,
|
| 1368 |
+
"eval_loss": 0.38055145740509033,
|
| 1369 |
+
"eval_runtime": 1.7219,
|
| 1370 |
+
"eval_samples_per_second": 18.584,
|
| 1371 |
+
"eval_steps_per_second": 9.292,
|
| 1372 |
+
"eval_wer_score": 4.047411918225316,
|
| 1373 |
+
"step": 4550
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 2.85,
|
| 1377 |
+
"learning_rate": 2.557755775577558e-06,
|
| 1378 |
+
"loss": 0.3658,
|
| 1379 |
+
"step": 4600
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 2.85,
|
| 1383 |
+
"eval_loss": 0.3797268867492676,
|
| 1384 |
+
"eval_runtime": 1.7777,
|
| 1385 |
+
"eval_samples_per_second": 18.0,
|
| 1386 |
+
"eval_steps_per_second": 9.0,
|
| 1387 |
+
"eval_wer_score": 4.038712483688561,
|
| 1388 |
+
"step": 4600
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.88,
|
| 1392 |
+
"learning_rate": 2.042079207920792e-06,
|
| 1393 |
+
"loss": 0.3661,
|
| 1394 |
+
"step": 4650
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 2.88,
|
| 1398 |
+
"eval_loss": 0.37951183319091797,
|
| 1399 |
+
"eval_runtime": 1.7219,
|
| 1400 |
+
"eval_samples_per_second": 18.584,
|
| 1401 |
+
"eval_steps_per_second": 9.292,
|
| 1402 |
+
"eval_wer_score": 4.044367116137451,
|
| 1403 |
+
"step": 4650
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.91,
|
| 1407 |
+
"learning_rate": 1.5264026402640265e-06,
|
| 1408 |
+
"loss": 0.3679,
|
| 1409 |
+
"step": 4700
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.91,
|
| 1413 |
+
"eval_loss": 0.37964126467704773,
|
| 1414 |
+
"eval_runtime": 1.7634,
|
| 1415 |
+
"eval_samples_per_second": 18.146,
|
| 1416 |
+
"eval_steps_per_second": 9.073,
|
| 1417 |
+
"eval_wer_score": 4.043062200956938,
|
| 1418 |
+
"step": 4700
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.94,
|
| 1422 |
+
"learning_rate": 1.0107260726072606e-06,
|
| 1423 |
+
"loss": 0.3667,
|
| 1424 |
+
"step": 4750
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.94,
|
| 1428 |
+
"eval_loss": 0.37969282269477844,
|
| 1429 |
+
"eval_runtime": 1.7225,
|
| 1430 |
+
"eval_samples_per_second": 18.577,
|
| 1431 |
+
"eval_steps_per_second": 9.289,
|
| 1432 |
+
"eval_wer_score": 4.039582427142236,
|
| 1433 |
+
"step": 4750
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.97,
|
| 1437 |
+
"learning_rate": 4.950495049504951e-07,
|
| 1438 |
+
"loss": 0.3671,
|
| 1439 |
+
"step": 4800
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.97,
|
| 1443 |
+
"eval_loss": 0.3793087899684906,
|
| 1444 |
+
"eval_runtime": 1.7729,
|
| 1445 |
+
"eval_samples_per_second": 18.049,
|
| 1446 |
+
"eval_steps_per_second": 9.025,
|
| 1447 |
+
"eval_wer_score": 4.044802087864289,
|
| 1448 |
+
"step": 4800
|
| 1449 |
+
}
|
| 1450 |
+
],
|
| 1451 |
+
"max_steps": 4848,
|
| 1452 |
+
"num_train_epochs": 3,
|
| 1453 |
+
"total_flos": 1.39557801614635e+18,
|
| 1454 |
+
"trial_name": null,
|
| 1455 |
+
"trial_params": null
|
| 1456 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e9297a038b204e730a2a68a3d19b6a7b7419ea145ba5f42f309eba4ae0bba33
|
| 3 |
+
size 4091
|