Upload 11 files
Browse files- config.json +10 -8
- model.safetensors +2 -2
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
- trainer_state.json +714 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
CHANGED
|
@@ -1,12 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"author": "Heewon Jeon([email protected])",
|
| 8 |
"classifier_dropout": null,
|
| 9 |
-
"
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
|
@@ -17,7 +16,6 @@
|
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 3072,
|
| 20 |
-
"kobert_version": 1.0,
|
| 21 |
"label2id": {
|
| 22 |
"LABEL_0": 0,
|
| 23 |
"LABEL_1": 1,
|
|
@@ -25,15 +23,19 @@
|
|
| 25 |
},
|
| 26 |
"layer_norm_eps": 1e-12,
|
| 27 |
"max_position_embeddings": 512,
|
| 28 |
-
"model_type": "
|
| 29 |
"num_attention_heads": 12,
|
| 30 |
"num_hidden_layers": 12,
|
| 31 |
-
"pad_token_id":
|
| 32 |
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
"transformers_version": "4.45.1",
|
| 36 |
"type_vocab_size": 2,
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "monologg/koelectra-base-v3-discriminator",
|
| 3 |
"architectures": [
|
| 4 |
+
"ElectraForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
|
|
|
| 16 |
},
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 3072,
|
|
|
|
| 19 |
"label2id": {
|
| 20 |
"LABEL_0": 0,
|
| 21 |
"LABEL_1": 1,
|
|
|
|
| 23 |
},
|
| 24 |
"layer_norm_eps": 1e-12,
|
| 25 |
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "electra",
|
| 27 |
"num_attention_heads": 12,
|
| 28 |
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
"position_embedding_type": "absolute",
|
| 31 |
"problem_type": "single_label_classification",
|
| 32 |
+
"summary_activation": "gelu",
|
| 33 |
+
"summary_last_dropout": 0.1,
|
| 34 |
+
"summary_type": "first",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
"transformers_version": "4.45.1",
|
| 38 |
"type_vocab_size": 2,
|
| 39 |
"use_cache": true,
|
| 40 |
+
"vocab_size": 35000
|
| 41 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7ce6384be92f1c7f441e7d36892fd4af2d8942446e7ec62ab1300075d6eead1
|
| 3 |
+
size 451718748
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5080a9a6edc7288b55de6518de49d2b65f4886fd9e8e3d9c400a0b0a9920cdda
|
| 3 |
+
size 903551738
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38bdd138de6a56a2479d7804e54bf21693ad07775ca65e9e18d4fd68b3b67efc
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65fe7bfd1f7a265858dbc13c464e7304a5cf563b67c7f8c8477bb66cb89c2811
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -41,7 +41,7 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"clean_up_tokenization_spaces":
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
|
@@ -53,6 +53,6 @@
|
|
| 53 |
"strip_accents": null,
|
| 54 |
"timeout": 60,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
-
"tokenizer_class": "
|
| 57 |
"unk_token": "[UNK]"
|
| 58 |
}
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
|
|
|
| 53 |
"strip_accents": null,
|
| 54 |
"timeout": 60,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 57 |
"unk_token": "[UNK]"
|
| 58 |
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9008317338451696,
|
| 3 |
+
"best_model_checkpoint": "./checkpoints/monologg_koelectra-base-v3-discriminator\\checkpoint-4689",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4689,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03198976327575176,
|
| 13 |
+
"grad_norm": 1.8438289165496826,
|
| 14 |
+
"learning_rate": 1.9786734911494988e-05,
|
| 15 |
+
"loss": 0.9998,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06397952655150352,
|
| 20 |
+
"grad_norm": 4.708126544952393,
|
| 21 |
+
"learning_rate": 1.9573469822989978e-05,
|
| 22 |
+
"loss": 0.8181,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09596928982725528,
|
| 27 |
+
"grad_norm": 7.408482551574707,
|
| 28 |
+
"learning_rate": 1.9360204734484968e-05,
|
| 29 |
+
"loss": 0.6265,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12795905310300704,
|
| 34 |
+
"grad_norm": 6.211757183074951,
|
| 35 |
+
"learning_rate": 1.9146939645979955e-05,
|
| 36 |
+
"loss": 0.5046,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1599488163787588,
|
| 41 |
+
"grad_norm": 7.470839500427246,
|
| 42 |
+
"learning_rate": 1.8933674557474945e-05,
|
| 43 |
+
"loss": 0.5358,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19193857965451055,
|
| 48 |
+
"grad_norm": 2.0797882080078125,
|
| 49 |
+
"learning_rate": 1.872040946896993e-05,
|
| 50 |
+
"loss": 0.483,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22392834293026231,
|
| 55 |
+
"grad_norm": 14.55879020690918,
|
| 56 |
+
"learning_rate": 1.8507144380464918e-05,
|
| 57 |
+
"loss": 0.4462,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2559181062060141,
|
| 62 |
+
"grad_norm": 3.5867443084716797,
|
| 63 |
+
"learning_rate": 1.8293879291959908e-05,
|
| 64 |
+
"loss": 0.4348,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.28790786948176583,
|
| 69 |
+
"grad_norm": 11.995755195617676,
|
| 70 |
+
"learning_rate": 1.8080614203454897e-05,
|
| 71 |
+
"loss": 0.4236,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3198976327575176,
|
| 76 |
+
"grad_norm": 7.211252689361572,
|
| 77 |
+
"learning_rate": 1.7867349114949884e-05,
|
| 78 |
+
"loss": 0.4099,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.35188739603326935,
|
| 83 |
+
"grad_norm": 5.884838581085205,
|
| 84 |
+
"learning_rate": 1.7654084026444874e-05,
|
| 85 |
+
"loss": 0.4265,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3838771593090211,
|
| 90 |
+
"grad_norm": 4.443331241607666,
|
| 91 |
+
"learning_rate": 1.744081893793986e-05,
|
| 92 |
+
"loss": 0.3863,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.41586692258477287,
|
| 97 |
+
"grad_norm": 3.68717622756958,
|
| 98 |
+
"learning_rate": 1.7227553849434847e-05,
|
| 99 |
+
"loss": 0.4244,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.44785668586052463,
|
| 104 |
+
"grad_norm": 4.4258599281311035,
|
| 105 |
+
"learning_rate": 1.7014288760929837e-05,
|
| 106 |
+
"loss": 0.3701,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4798464491362764,
|
| 111 |
+
"grad_norm": 8.484159469604492,
|
| 112 |
+
"learning_rate": 1.6801023672424827e-05,
|
| 113 |
+
"loss": 0.4079,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5118362124120281,
|
| 118 |
+
"grad_norm": 8.976361274719238,
|
| 119 |
+
"learning_rate": 1.6587758583919813e-05,
|
| 120 |
+
"loss": 0.3413,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5438259756877799,
|
| 125 |
+
"grad_norm": 7.113468170166016,
|
| 126 |
+
"learning_rate": 1.6374493495414803e-05,
|
| 127 |
+
"loss": 0.3928,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5758157389635317,
|
| 132 |
+
"grad_norm": 7.242956161499023,
|
| 133 |
+
"learning_rate": 1.616122840690979e-05,
|
| 134 |
+
"loss": 0.4013,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6078055022392834,
|
| 139 |
+
"grad_norm": 6.204492092132568,
|
| 140 |
+
"learning_rate": 1.5947963318404776e-05,
|
| 141 |
+
"loss": 0.3838,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6397952655150352,
|
| 146 |
+
"grad_norm": 5.312352180480957,
|
| 147 |
+
"learning_rate": 1.5734698229899766e-05,
|
| 148 |
+
"loss": 0.3838,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6717850287907869,
|
| 153 |
+
"grad_norm": 22.331918716430664,
|
| 154 |
+
"learning_rate": 1.5521433141394756e-05,
|
| 155 |
+
"loss": 0.3618,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7037747920665387,
|
| 160 |
+
"grad_norm": 11.372283935546875,
|
| 161 |
+
"learning_rate": 1.5308168052889743e-05,
|
| 162 |
+
"loss": 0.3486,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7357645553422905,
|
| 167 |
+
"grad_norm": 31.921972274780273,
|
| 168 |
+
"learning_rate": 1.5094902964384733e-05,
|
| 169 |
+
"loss": 0.3807,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7677543186180422,
|
| 174 |
+
"grad_norm": 6.360013484954834,
|
| 175 |
+
"learning_rate": 1.488163787587972e-05,
|
| 176 |
+
"loss": 0.3903,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.799744081893794,
|
| 181 |
+
"grad_norm": 5.0191330909729,
|
| 182 |
+
"learning_rate": 1.4668372787374708e-05,
|
| 183 |
+
"loss": 0.3477,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8317338451695457,
|
| 188 |
+
"grad_norm": 20.319231033325195,
|
| 189 |
+
"learning_rate": 1.4455107698869698e-05,
|
| 190 |
+
"loss": 0.3193,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8637236084452975,
|
| 195 |
+
"grad_norm": 3.2279179096221924,
|
| 196 |
+
"learning_rate": 1.4241842610364684e-05,
|
| 197 |
+
"loss": 0.3583,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8957133717210493,
|
| 202 |
+
"grad_norm": 5.339118480682373,
|
| 203 |
+
"learning_rate": 1.4028577521859672e-05,
|
| 204 |
+
"loss": 0.3343,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.927703134996801,
|
| 209 |
+
"grad_norm": 3.4250569343566895,
|
| 210 |
+
"learning_rate": 1.3815312433354662e-05,
|
| 211 |
+
"loss": 0.3756,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9596928982725528,
|
| 216 |
+
"grad_norm": 7.723750591278076,
|
| 217 |
+
"learning_rate": 1.3602047344849649e-05,
|
| 218 |
+
"loss": 0.3342,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9916826615483045,
|
| 223 |
+
"grad_norm": 9.071324348449707,
|
| 224 |
+
"learning_rate": 1.3388782256344637e-05,
|
| 225 |
+
"loss": 0.3282,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0,
|
| 230 |
+
"eval_accuracy": 0.8848368522072937,
|
| 231 |
+
"eval_f1": 0.8749968140479337,
|
| 232 |
+
"eval_loss": 0.3197398781776428,
|
| 233 |
+
"eval_runtime": 69.8877,
|
| 234 |
+
"eval_samples_per_second": 44.729,
|
| 235 |
+
"eval_steps_per_second": 2.804,
|
| 236 |
+
"step": 1563
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.0236724248240563,
|
| 240 |
+
"grad_norm": 3.9245243072509766,
|
| 241 |
+
"learning_rate": 1.3175517167839627e-05,
|
| 242 |
+
"loss": 0.2311,
|
| 243 |
+
"step": 1600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.055662188099808,
|
| 247 |
+
"grad_norm": 13.951614379882812,
|
| 248 |
+
"learning_rate": 1.2962252079334613e-05,
|
| 249 |
+
"loss": 0.2844,
|
| 250 |
+
"step": 1650
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.0876519513755598,
|
| 254 |
+
"grad_norm": 8.549053192138672,
|
| 255 |
+
"learning_rate": 1.2748986990829602e-05,
|
| 256 |
+
"loss": 0.2573,
|
| 257 |
+
"step": 1700
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.1196417146513116,
|
| 261 |
+
"grad_norm": 7.1960835456848145,
|
| 262 |
+
"learning_rate": 1.2535721902324592e-05,
|
| 263 |
+
"loss": 0.2515,
|
| 264 |
+
"step": 1750
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.1516314779270633,
|
| 268 |
+
"grad_norm": 3.4280333518981934,
|
| 269 |
+
"learning_rate": 1.2322456813819578e-05,
|
| 270 |
+
"loss": 0.3032,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.183621241202815,
|
| 275 |
+
"grad_norm": 7.896517753601074,
|
| 276 |
+
"learning_rate": 1.2109191725314566e-05,
|
| 277 |
+
"loss": 0.2503,
|
| 278 |
+
"step": 1850
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.2156110044785668,
|
| 282 |
+
"grad_norm": 3.302367687225342,
|
| 283 |
+
"learning_rate": 1.1895926636809556e-05,
|
| 284 |
+
"loss": 0.2815,
|
| 285 |
+
"step": 1900
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.2476007677543186,
|
| 289 |
+
"grad_norm": 7.449910640716553,
|
| 290 |
+
"learning_rate": 1.1682661548304543e-05,
|
| 291 |
+
"loss": 0.2483,
|
| 292 |
+
"step": 1950
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.2795905310300704,
|
| 296 |
+
"grad_norm": 6.277085304260254,
|
| 297 |
+
"learning_rate": 1.1469396459799531e-05,
|
| 298 |
+
"loss": 0.2709,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.3115802943058221,
|
| 303 |
+
"grad_norm": 4.672796726226807,
|
| 304 |
+
"learning_rate": 1.1256131371294521e-05,
|
| 305 |
+
"loss": 0.2555,
|
| 306 |
+
"step": 2050
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.3435700575815739,
|
| 310 |
+
"grad_norm": 11.666603088378906,
|
| 311 |
+
"learning_rate": 1.1042866282789508e-05,
|
| 312 |
+
"loss": 0.2381,
|
| 313 |
+
"step": 2100
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.3755598208573256,
|
| 317 |
+
"grad_norm": 9.201951026916504,
|
| 318 |
+
"learning_rate": 1.0829601194284496e-05,
|
| 319 |
+
"loss": 0.2762,
|
| 320 |
+
"step": 2150
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.4075495841330774,
|
| 324 |
+
"grad_norm": 2.2189481258392334,
|
| 325 |
+
"learning_rate": 1.0616336105779486e-05,
|
| 326 |
+
"loss": 0.2466,
|
| 327 |
+
"step": 2200
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.4395393474088292,
|
| 331 |
+
"grad_norm": 8.02763557434082,
|
| 332 |
+
"learning_rate": 1.0403071017274472e-05,
|
| 333 |
+
"loss": 0.2556,
|
| 334 |
+
"step": 2250
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.471529110684581,
|
| 338 |
+
"grad_norm": 2.0652530193328857,
|
| 339 |
+
"learning_rate": 1.018980592876946e-05,
|
| 340 |
+
"loss": 0.2789,
|
| 341 |
+
"step": 2300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.5035188739603327,
|
| 345 |
+
"grad_norm": 13.113646507263184,
|
| 346 |
+
"learning_rate": 9.976540840264449e-06,
|
| 347 |
+
"loss": 0.2235,
|
| 348 |
+
"step": 2350
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.5355086372360844,
|
| 352 |
+
"grad_norm": 10.362279891967773,
|
| 353 |
+
"learning_rate": 9.763275751759437e-06,
|
| 354 |
+
"loss": 0.2482,
|
| 355 |
+
"step": 2400
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.5674984005118362,
|
| 359 |
+
"grad_norm": 1.568915843963623,
|
| 360 |
+
"learning_rate": 9.550010663254427e-06,
|
| 361 |
+
"loss": 0.2622,
|
| 362 |
+
"step": 2450
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.599488163787588,
|
| 366 |
+
"grad_norm": 10.095715522766113,
|
| 367 |
+
"learning_rate": 9.336745574749414e-06,
|
| 368 |
+
"loss": 0.2668,
|
| 369 |
+
"step": 2500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.6314779270633397,
|
| 373 |
+
"grad_norm": 12.999874114990234,
|
| 374 |
+
"learning_rate": 9.123480486244403e-06,
|
| 375 |
+
"loss": 0.2361,
|
| 376 |
+
"step": 2550
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.6634676903390915,
|
| 380 |
+
"grad_norm": 7.512565612792969,
|
| 381 |
+
"learning_rate": 8.910215397739392e-06,
|
| 382 |
+
"loss": 0.2646,
|
| 383 |
+
"step": 2600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.6954574536148432,
|
| 387 |
+
"grad_norm": 6.645097732543945,
|
| 388 |
+
"learning_rate": 8.696950309234378e-06,
|
| 389 |
+
"loss": 0.2478,
|
| 390 |
+
"step": 2650
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.727447216890595,
|
| 394 |
+
"grad_norm": 4.22629976272583,
|
| 395 |
+
"learning_rate": 8.483685220729368e-06,
|
| 396 |
+
"loss": 0.2686,
|
| 397 |
+
"step": 2700
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.7594369801663468,
|
| 401 |
+
"grad_norm": 8.55104923248291,
|
| 402 |
+
"learning_rate": 8.270420132224356e-06,
|
| 403 |
+
"loss": 0.2615,
|
| 404 |
+
"step": 2750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.7914267434420985,
|
| 408 |
+
"grad_norm": 4.150308132171631,
|
| 409 |
+
"learning_rate": 8.057155043719343e-06,
|
| 410 |
+
"loss": 0.2669,
|
| 411 |
+
"step": 2800
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.8234165067178503,
|
| 415 |
+
"grad_norm": 15.736576080322266,
|
| 416 |
+
"learning_rate": 7.843889955214333e-06,
|
| 417 |
+
"loss": 0.252,
|
| 418 |
+
"step": 2850
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.855406269993602,
|
| 422 |
+
"grad_norm": 1.219308853149414,
|
| 423 |
+
"learning_rate": 7.630624866709321e-06,
|
| 424 |
+
"loss": 0.2619,
|
| 425 |
+
"step": 2900
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.8873960332693538,
|
| 429 |
+
"grad_norm": 4.5792999267578125,
|
| 430 |
+
"learning_rate": 7.4173597782043085e-06,
|
| 431 |
+
"loss": 0.2516,
|
| 432 |
+
"step": 2950
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.9193857965451055,
|
| 436 |
+
"grad_norm": 7.346240043640137,
|
| 437 |
+
"learning_rate": 7.204094689699297e-06,
|
| 438 |
+
"loss": 0.2374,
|
| 439 |
+
"step": 3000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.9513755598208573,
|
| 443 |
+
"grad_norm": 15.958673477172852,
|
| 444 |
+
"learning_rate": 6.990829601194286e-06,
|
| 445 |
+
"loss": 0.2568,
|
| 446 |
+
"step": 3050
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.983365323096609,
|
| 450 |
+
"grad_norm": 8.143491744995117,
|
| 451 |
+
"learning_rate": 6.777564512689273e-06,
|
| 452 |
+
"loss": 0.2196,
|
| 453 |
+
"step": 3100
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.0,
|
| 457 |
+
"eval_accuracy": 0.8902751119641714,
|
| 458 |
+
"eval_f1": 0.8821468217693207,
|
| 459 |
+
"eval_loss": 0.35885584354400635,
|
| 460 |
+
"eval_runtime": 70.4611,
|
| 461 |
+
"eval_samples_per_second": 44.365,
|
| 462 |
+
"eval_steps_per_second": 2.782,
|
| 463 |
+
"step": 3126
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.015355086372361,
|
| 467 |
+
"grad_norm": 2.4161245822906494,
|
| 468 |
+
"learning_rate": 6.5642994241842614e-06,
|
| 469 |
+
"loss": 0.211,
|
| 470 |
+
"step": 3150
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.0473448496481126,
|
| 474 |
+
"grad_norm": 6.2580156326293945,
|
| 475 |
+
"learning_rate": 6.3510343356792505e-06,
|
| 476 |
+
"loss": 0.1819,
|
| 477 |
+
"step": 3200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.0793346129238643,
|
| 481 |
+
"grad_norm": 17.149974822998047,
|
| 482 |
+
"learning_rate": 6.137769247174238e-06,
|
| 483 |
+
"loss": 0.188,
|
| 484 |
+
"step": 3250
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.111324376199616,
|
| 488 |
+
"grad_norm": 4.2034382820129395,
|
| 489 |
+
"learning_rate": 5.924504158669226e-06,
|
| 490 |
+
"loss": 0.1653,
|
| 491 |
+
"step": 3300
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.143314139475368,
|
| 495 |
+
"grad_norm": 7.357328414916992,
|
| 496 |
+
"learning_rate": 5.711239070164215e-06,
|
| 497 |
+
"loss": 0.1748,
|
| 498 |
+
"step": 3350
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.1753039027511196,
|
| 502 |
+
"grad_norm": 13.677566528320312,
|
| 503 |
+
"learning_rate": 5.497973981659203e-06,
|
| 504 |
+
"loss": 0.2177,
|
| 505 |
+
"step": 3400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.2072936660268714,
|
| 509 |
+
"grad_norm": 8.67300033569336,
|
| 510 |
+
"learning_rate": 5.284708893154191e-06,
|
| 511 |
+
"loss": 0.1571,
|
| 512 |
+
"step": 3450
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.239283429302623,
|
| 516 |
+
"grad_norm": 22.893770217895508,
|
| 517 |
+
"learning_rate": 5.07144380464918e-06,
|
| 518 |
+
"loss": 0.2009,
|
| 519 |
+
"step": 3500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.271273192578375,
|
| 523 |
+
"grad_norm": 3.602328300476074,
|
| 524 |
+
"learning_rate": 4.858178716144167e-06,
|
| 525 |
+
"loss": 0.1329,
|
| 526 |
+
"step": 3550
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.3032629558541267,
|
| 530 |
+
"grad_norm": 18.8084659576416,
|
| 531 |
+
"learning_rate": 4.644913627639156e-06,
|
| 532 |
+
"loss": 0.1814,
|
| 533 |
+
"step": 3600
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.3352527191298784,
|
| 537 |
+
"grad_norm": 0.4535435736179352,
|
| 538 |
+
"learning_rate": 4.431648539134144e-06,
|
| 539 |
+
"loss": 0.2069,
|
| 540 |
+
"step": 3650
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.36724248240563,
|
| 544 |
+
"grad_norm": 11.971237182617188,
|
| 545 |
+
"learning_rate": 4.218383450629132e-06,
|
| 546 |
+
"loss": 0.188,
|
| 547 |
+
"step": 3700
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 2.399232245681382,
|
| 551 |
+
"grad_norm": 5.598160266876221,
|
| 552 |
+
"learning_rate": 4.005118362124121e-06,
|
| 553 |
+
"loss": 0.1943,
|
| 554 |
+
"step": 3750
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.4312220089571337,
|
| 558 |
+
"grad_norm": 11.97499942779541,
|
| 559 |
+
"learning_rate": 3.791853273619109e-06,
|
| 560 |
+
"loss": 0.2155,
|
| 561 |
+
"step": 3800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.4632117722328855,
|
| 565 |
+
"grad_norm": 9.149175643920898,
|
| 566 |
+
"learning_rate": 3.5785881851140968e-06,
|
| 567 |
+
"loss": 0.2025,
|
| 568 |
+
"step": 3850
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.495201535508637,
|
| 572 |
+
"grad_norm": 7.965933799743652,
|
| 573 |
+
"learning_rate": 3.3653230966090854e-06,
|
| 574 |
+
"loss": 0.2121,
|
| 575 |
+
"step": 3900
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.527191298784389,
|
| 579 |
+
"grad_norm": 9.397235870361328,
|
| 580 |
+
"learning_rate": 3.1520580081040737e-06,
|
| 581 |
+
"loss": 0.1724,
|
| 582 |
+
"step": 3950
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.5591810620601407,
|
| 586 |
+
"grad_norm": 14.580031394958496,
|
| 587 |
+
"learning_rate": 2.9387929195990615e-06,
|
| 588 |
+
"loss": 0.1636,
|
| 589 |
+
"step": 4000
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.5911708253358925,
|
| 593 |
+
"grad_norm": 2.2896785736083984,
|
| 594 |
+
"learning_rate": 2.72552783109405e-06,
|
| 595 |
+
"loss": 0.1603,
|
| 596 |
+
"step": 4050
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.6231605886116443,
|
| 600 |
+
"grad_norm": 22.936344146728516,
|
| 601 |
+
"learning_rate": 2.5122627425890384e-06,
|
| 602 |
+
"loss": 0.1944,
|
| 603 |
+
"step": 4100
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.655150351887396,
|
| 607 |
+
"grad_norm": 37.436187744140625,
|
| 608 |
+
"learning_rate": 2.2989976540840266e-06,
|
| 609 |
+
"loss": 0.2059,
|
| 610 |
+
"step": 4150
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.6871401151631478,
|
| 614 |
+
"grad_norm": 26.6770076751709,
|
| 615 |
+
"learning_rate": 2.085732565579015e-06,
|
| 616 |
+
"loss": 0.1448,
|
| 617 |
+
"step": 4200
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.7191298784388995,
|
| 621 |
+
"grad_norm": 20.561311721801758,
|
| 622 |
+
"learning_rate": 1.872467477074003e-06,
|
| 623 |
+
"loss": 0.2094,
|
| 624 |
+
"step": 4250
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.7511196417146513,
|
| 628 |
+
"grad_norm": 4.114218711853027,
|
| 629 |
+
"learning_rate": 1.6592023885689915e-06,
|
| 630 |
+
"loss": 0.1682,
|
| 631 |
+
"step": 4300
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.783109404990403,
|
| 635 |
+
"grad_norm": 27.9166202545166,
|
| 636 |
+
"learning_rate": 1.4459373000639796e-06,
|
| 637 |
+
"loss": 0.1931,
|
| 638 |
+
"step": 4350
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.815099168266155,
|
| 642 |
+
"grad_norm": 13.576592445373535,
|
| 643 |
+
"learning_rate": 1.2326722115589678e-06,
|
| 644 |
+
"loss": 0.1989,
|
| 645 |
+
"step": 4400
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.8470889315419066,
|
| 649 |
+
"grad_norm": 4.428896427154541,
|
| 650 |
+
"learning_rate": 1.019407123053956e-06,
|
| 651 |
+
"loss": 0.18,
|
| 652 |
+
"step": 4450
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.8790786948176583,
|
| 656 |
+
"grad_norm": 10.087977409362793,
|
| 657 |
+
"learning_rate": 8.061420345489445e-07,
|
| 658 |
+
"loss": 0.2102,
|
| 659 |
+
"step": 4500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.91106845809341,
|
| 663 |
+
"grad_norm": 16.517681121826172,
|
| 664 |
+
"learning_rate": 5.928769460439326e-07,
|
| 665 |
+
"loss": 0.1662,
|
| 666 |
+
"step": 4550
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.943058221369162,
|
| 670 |
+
"grad_norm": 15.329133987426758,
|
| 671 |
+
"learning_rate": 3.796118575389209e-07,
|
| 672 |
+
"loss": 0.1997,
|
| 673 |
+
"step": 4600
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.9750479846449136,
|
| 677 |
+
"grad_norm": 18.751319885253906,
|
| 678 |
+
"learning_rate": 1.6634676903390917e-07,
|
| 679 |
+
"loss": 0.1924,
|
| 680 |
+
"step": 4650
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.0,
|
| 684 |
+
"eval_accuracy": 0.9008317338451696,
|
| 685 |
+
"eval_f1": 0.892446816336566,
|
| 686 |
+
"eval_loss": 0.3720133900642395,
|
| 687 |
+
"eval_runtime": 71.8708,
|
| 688 |
+
"eval_samples_per_second": 43.495,
|
| 689 |
+
"eval_steps_per_second": 2.727,
|
| 690 |
+
"step": 4689
|
| 691 |
+
}
|
| 692 |
+
],
|
| 693 |
+
"logging_steps": 50,
|
| 694 |
+
"max_steps": 4689,
|
| 695 |
+
"num_input_tokens_seen": 0,
|
| 696 |
+
"num_train_epochs": 3,
|
| 697 |
+
"save_steps": 500,
|
| 698 |
+
"stateful_callbacks": {
|
| 699 |
+
"TrainerControl": {
|
| 700 |
+
"args": {
|
| 701 |
+
"should_epoch_stop": false,
|
| 702 |
+
"should_evaluate": false,
|
| 703 |
+
"should_log": false,
|
| 704 |
+
"should_save": true,
|
| 705 |
+
"should_training_stop": true
|
| 706 |
+
},
|
| 707 |
+
"attributes": {}
|
| 708 |
+
}
|
| 709 |
+
},
|
| 710 |
+
"total_flos": 837402132857850.0,
|
| 711 |
+
"train_batch_size": 16,
|
| 712 |
+
"trial_name": null,
|
| 713 |
+
"trial_params": null
|
| 714 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80719dde8ee12368c548b9d0fd820c908d79ccc5612eb348afb50e76be1caccc
|
| 3 |
+
size 5240
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|