Upload folder using huggingface_hub
Browse files- xlmr_hope_ml/checkpoint-8190/config.json +28 -0
- xlmr_hope_ml/checkpoint-8190/model.safetensors +3 -0
- xlmr_hope_ml/checkpoint-8190/optimizer.pt +3 -0
- xlmr_hope_ml/checkpoint-8190/rng_state.pth +3 -0
- xlmr_hope_ml/checkpoint-8190/scheduler.pt +3 -0
- xlmr_hope_ml/checkpoint-8190/trainer_state.json +1225 -0
- xlmr_hope_ml/checkpoint-8190/training_args.bin +3 -0
xlmr_hope_ml/checkpoint-8190/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 250002
|
| 28 |
+
}
|
xlmr_hope_ml/checkpoint-8190/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:223d30157ac6007a18b19a5ccd57763d3ffec8aa6d87431aa421a62ed73c0406
|
| 3 |
+
size 1112205008
|
xlmr_hope_ml/checkpoint-8190/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d47d0afc1eb876b23db47d6217b313c3fd8a4519e727fd2683d44394a27b65f
|
| 3 |
+
size 2224532875
|
xlmr_hope_ml/checkpoint-8190/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0acf01d7b40d568a2dd5d875948460fb1a4f1c2199469f4b512628826c0a8b0f
|
| 3 |
+
size 14645
|
xlmr_hope_ml/checkpoint-8190/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45338ca571085cd8a7411a7f31810ec518eedb9269c9c2db8984e82e9065bb53
|
| 3 |
+
size 1465
|
xlmr_hope_ml/checkpoint-8190/trainer_state.json
ADDED
|
@@ -0,0 +1,1225 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 8190,
|
| 3 |
+
"best_metric": 0.847602022392802,
|
| 4 |
+
"best_model_checkpoint": "./malviz_models1/xlmr_hope_ml/checkpoint-8190",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 8190,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.030525030525030524,
|
| 14 |
+
"grad_norm": 6.407163619995117,
|
| 15 |
+
"learning_rate": 1.9880341880341883e-05,
|
| 16 |
+
"loss": 0.6391,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06105006105006105,
|
| 21 |
+
"grad_norm": 32.01091003417969,
|
| 22 |
+
"learning_rate": 1.9758241758241762e-05,
|
| 23 |
+
"loss": 0.6692,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09157509157509157,
|
| 28 |
+
"grad_norm": 15.060482025146484,
|
| 29 |
+
"learning_rate": 1.9636141636141637e-05,
|
| 30 |
+
"loss": 0.6613,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1221001221001221,
|
| 35 |
+
"grad_norm": 5.653907299041748,
|
| 36 |
+
"learning_rate": 1.9514041514041516e-05,
|
| 37 |
+
"loss": 0.5875,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15262515262515264,
|
| 42 |
+
"grad_norm": 19.34565544128418,
|
| 43 |
+
"learning_rate": 1.9391941391941395e-05,
|
| 44 |
+
"loss": 0.6016,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.18315018315018314,
|
| 49 |
+
"grad_norm": 16.258790969848633,
|
| 50 |
+
"learning_rate": 1.9269841269841273e-05,
|
| 51 |
+
"loss": 0.5973,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.21367521367521367,
|
| 56 |
+
"grad_norm": 15.239129066467285,
|
| 57 |
+
"learning_rate": 1.914774114774115e-05,
|
| 58 |
+
"loss": 0.5859,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2442002442002442,
|
| 63 |
+
"grad_norm": 37.504249572753906,
|
| 64 |
+
"learning_rate": 1.9025641025641027e-05,
|
| 65 |
+
"loss": 0.606,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.27472527472527475,
|
| 70 |
+
"grad_norm": 28.16376304626465,
|
| 71 |
+
"learning_rate": 1.8903540903540906e-05,
|
| 72 |
+
"loss": 0.5809,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3052503052503053,
|
| 77 |
+
"grad_norm": 58.881919860839844,
|
| 78 |
+
"learning_rate": 1.878144078144078e-05,
|
| 79 |
+
"loss": 0.611,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33577533577533575,
|
| 84 |
+
"grad_norm": 8.836572647094727,
|
| 85 |
+
"learning_rate": 1.865934065934066e-05,
|
| 86 |
+
"loss": 0.6063,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3663003663003663,
|
| 91 |
+
"grad_norm": 4.018986701965332,
|
| 92 |
+
"learning_rate": 1.853724053724054e-05,
|
| 93 |
+
"loss": 0.6199,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3968253968253968,
|
| 98 |
+
"grad_norm": 5.098257064819336,
|
| 99 |
+
"learning_rate": 1.8415140415140414e-05,
|
| 100 |
+
"loss": 0.5779,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.42735042735042733,
|
| 105 |
+
"grad_norm": 13.460134506225586,
|
| 106 |
+
"learning_rate": 1.8293040293040293e-05,
|
| 107 |
+
"loss": 0.546,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.45787545787545786,
|
| 112 |
+
"grad_norm": 14.35595417022705,
|
| 113 |
+
"learning_rate": 1.817094017094017e-05,
|
| 114 |
+
"loss": 0.5757,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4884004884004884,
|
| 119 |
+
"grad_norm": 11.146136283874512,
|
| 120 |
+
"learning_rate": 1.804884004884005e-05,
|
| 121 |
+
"loss": 0.486,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.518925518925519,
|
| 126 |
+
"grad_norm": 27.647869110107422,
|
| 127 |
+
"learning_rate": 1.792673992673993e-05,
|
| 128 |
+
"loss": 0.5923,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5494505494505495,
|
| 133 |
+
"grad_norm": 26.801227569580078,
|
| 134 |
+
"learning_rate": 1.7804639804639804e-05,
|
| 135 |
+
"loss": 0.5901,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.57997557997558,
|
| 140 |
+
"grad_norm": 5.888443946838379,
|
| 141 |
+
"learning_rate": 1.7682539682539683e-05,
|
| 142 |
+
"loss": 0.5396,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6105006105006106,
|
| 147 |
+
"grad_norm": 6.846390247344971,
|
| 148 |
+
"learning_rate": 1.7560439560439562e-05,
|
| 149 |
+
"loss": 0.494,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6410256410256411,
|
| 154 |
+
"grad_norm": 5.446658611297607,
|
| 155 |
+
"learning_rate": 1.743833943833944e-05,
|
| 156 |
+
"loss": 0.5021,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6715506715506715,
|
| 161 |
+
"grad_norm": 9.575170516967773,
|
| 162 |
+
"learning_rate": 1.731623931623932e-05,
|
| 163 |
+
"loss": 0.5124,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.702075702075702,
|
| 168 |
+
"grad_norm": 11.39124870300293,
|
| 169 |
+
"learning_rate": 1.7194139194139198e-05,
|
| 170 |
+
"loss": 0.5161,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.7326007326007326,
|
| 175 |
+
"grad_norm": 8.475871086120605,
|
| 176 |
+
"learning_rate": 1.7072039072039073e-05,
|
| 177 |
+
"loss": 0.487,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.7631257631257631,
|
| 182 |
+
"grad_norm": 5.726651191711426,
|
| 183 |
+
"learning_rate": 1.6949938949938952e-05,
|
| 184 |
+
"loss": 0.4989,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.7936507936507936,
|
| 189 |
+
"grad_norm": 6.620838165283203,
|
| 190 |
+
"learning_rate": 1.682783882783883e-05,
|
| 191 |
+
"loss": 0.459,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.8241758241758241,
|
| 196 |
+
"grad_norm": 14.812911987304688,
|
| 197 |
+
"learning_rate": 1.670573870573871e-05,
|
| 198 |
+
"loss": 0.5003,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8547008547008547,
|
| 203 |
+
"grad_norm": 7.2252068519592285,
|
| 204 |
+
"learning_rate": 1.6583638583638585e-05,
|
| 205 |
+
"loss": 0.4551,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.8852258852258852,
|
| 210 |
+
"grad_norm": 3.8601975440979004,
|
| 211 |
+
"learning_rate": 1.6461538461538463e-05,
|
| 212 |
+
"loss": 0.4581,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.9157509157509157,
|
| 217 |
+
"grad_norm": 13.167617797851562,
|
| 218 |
+
"learning_rate": 1.6339438339438342e-05,
|
| 219 |
+
"loss": 0.4876,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.9462759462759462,
|
| 224 |
+
"grad_norm": 7.253393650054932,
|
| 225 |
+
"learning_rate": 1.6217338217338217e-05,
|
| 226 |
+
"loss": 0.4525,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.9768009768009768,
|
| 231 |
+
"grad_norm": 8.873754501342773,
|
| 232 |
+
"learning_rate": 1.6095238095238096e-05,
|
| 233 |
+
"loss": 0.4631,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0,
|
| 238 |
+
"eval_accuracy": 0.7461459403905447,
|
| 239 |
+
"eval_f1": 0.766364618875453,
|
| 240 |
+
"eval_loss": 0.46973007917404175,
|
| 241 |
+
"eval_runtime": 3.4241,
|
| 242 |
+
"eval_samples_per_second": 284.161,
|
| 243 |
+
"eval_steps_per_second": 17.815,
|
| 244 |
+
"step": 1638
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.0073260073260073,
|
| 248 |
+
"grad_norm": 14.408209800720215,
|
| 249 |
+
"learning_rate": 1.5973137973137975e-05,
|
| 250 |
+
"loss": 0.4603,
|
| 251 |
+
"step": 1650
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.037851037851038,
|
| 255 |
+
"grad_norm": 22.586956024169922,
|
| 256 |
+
"learning_rate": 1.585103785103785e-05,
|
| 257 |
+
"loss": 0.4737,
|
| 258 |
+
"step": 1700
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.0683760683760684,
|
| 262 |
+
"grad_norm": 9.874870300292969,
|
| 263 |
+
"learning_rate": 1.572893772893773e-05,
|
| 264 |
+
"loss": 0.452,
|
| 265 |
+
"step": 1750
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.098901098901099,
|
| 269 |
+
"grad_norm": 24.893917083740234,
|
| 270 |
+
"learning_rate": 1.5606837606837608e-05,
|
| 271 |
+
"loss": 0.4263,
|
| 272 |
+
"step": 1800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.1294261294261294,
|
| 276 |
+
"grad_norm": 18.05025291442871,
|
| 277 |
+
"learning_rate": 1.5484737484737486e-05,
|
| 278 |
+
"loss": 0.4424,
|
| 279 |
+
"step": 1850
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.1599511599511598,
|
| 283 |
+
"grad_norm": 3.7677385807037354,
|
| 284 |
+
"learning_rate": 1.5362637362637365e-05,
|
| 285 |
+
"loss": 0.4099,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.1904761904761905,
|
| 290 |
+
"grad_norm": 9.057735443115234,
|
| 291 |
+
"learning_rate": 1.524053724053724e-05,
|
| 292 |
+
"loss": 0.4298,
|
| 293 |
+
"step": 1950
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.221001221001221,
|
| 297 |
+
"grad_norm": 9.04925537109375,
|
| 298 |
+
"learning_rate": 1.5118437118437119e-05,
|
| 299 |
+
"loss": 0.4629,
|
| 300 |
+
"step": 2000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.2515262515262515,
|
| 304 |
+
"grad_norm": 15.214876174926758,
|
| 305 |
+
"learning_rate": 1.4996336996336998e-05,
|
| 306 |
+
"loss": 0.3746,
|
| 307 |
+
"step": 2050
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.282051282051282,
|
| 311 |
+
"grad_norm": 14.752812385559082,
|
| 312 |
+
"learning_rate": 1.4874236874236877e-05,
|
| 313 |
+
"loss": 0.454,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.3125763125763126,
|
| 318 |
+
"grad_norm": 13.337708473205566,
|
| 319 |
+
"learning_rate": 1.4752136752136754e-05,
|
| 320 |
+
"loss": 0.4289,
|
| 321 |
+
"step": 2150
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.3431013431013432,
|
| 325 |
+
"grad_norm": 15.018891334533691,
|
| 326 |
+
"learning_rate": 1.463003663003663e-05,
|
| 327 |
+
"loss": 0.4298,
|
| 328 |
+
"step": 2200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.3736263736263736,
|
| 332 |
+
"grad_norm": 40.46508026123047,
|
| 333 |
+
"learning_rate": 1.450793650793651e-05,
|
| 334 |
+
"loss": 0.3758,
|
| 335 |
+
"step": 2250
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.404151404151404,
|
| 339 |
+
"grad_norm": 43.62735366821289,
|
| 340 |
+
"learning_rate": 1.4385836385836386e-05,
|
| 341 |
+
"loss": 0.4464,
|
| 342 |
+
"step": 2300
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.4346764346764347,
|
| 346 |
+
"grad_norm": 12.847195625305176,
|
| 347 |
+
"learning_rate": 1.4263736263736265e-05,
|
| 348 |
+
"loss": 0.4321,
|
| 349 |
+
"step": 2350
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.4652014652014653,
|
| 353 |
+
"grad_norm": 17.7137508392334,
|
| 354 |
+
"learning_rate": 1.4141636141636144e-05,
|
| 355 |
+
"loss": 0.4588,
|
| 356 |
+
"step": 2400
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.4957264957264957,
|
| 360 |
+
"grad_norm": 18.785490036010742,
|
| 361 |
+
"learning_rate": 1.4019536019536019e-05,
|
| 362 |
+
"loss": 0.3921,
|
| 363 |
+
"step": 2450
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.5262515262515262,
|
| 367 |
+
"grad_norm": 7.5587239265441895,
|
| 368 |
+
"learning_rate": 1.3897435897435898e-05,
|
| 369 |
+
"loss": 0.4384,
|
| 370 |
+
"step": 2500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.5567765567765568,
|
| 374 |
+
"grad_norm": 38.49454116821289,
|
| 375 |
+
"learning_rate": 1.3775335775335776e-05,
|
| 376 |
+
"loss": 0.4314,
|
| 377 |
+
"step": 2550
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.5873015873015874,
|
| 381 |
+
"grad_norm": 10.616717338562012,
|
| 382 |
+
"learning_rate": 1.3653235653235655e-05,
|
| 383 |
+
"loss": 0.4251,
|
| 384 |
+
"step": 2600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.6178266178266179,
|
| 388 |
+
"grad_norm": 13.551919937133789,
|
| 389 |
+
"learning_rate": 1.3531135531135532e-05,
|
| 390 |
+
"loss": 0.4647,
|
| 391 |
+
"step": 2650
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.6483516483516483,
|
| 395 |
+
"grad_norm": 22.2562313079834,
|
| 396 |
+
"learning_rate": 1.340903540903541e-05,
|
| 397 |
+
"loss": 0.4042,
|
| 398 |
+
"step": 2700
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.678876678876679,
|
| 402 |
+
"grad_norm": 113.62215423583984,
|
| 403 |
+
"learning_rate": 1.3286935286935288e-05,
|
| 404 |
+
"loss": 0.4039,
|
| 405 |
+
"step": 2750
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.7094017094017095,
|
| 409 |
+
"grad_norm": 17.464237213134766,
|
| 410 |
+
"learning_rate": 1.3164835164835165e-05,
|
| 411 |
+
"loss": 0.4271,
|
| 412 |
+
"step": 2800
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.73992673992674,
|
| 416 |
+
"grad_norm": 25.872488021850586,
|
| 417 |
+
"learning_rate": 1.3042735042735044e-05,
|
| 418 |
+
"loss": 0.4423,
|
| 419 |
+
"step": 2850
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.7704517704517704,
|
| 423 |
+
"grad_norm": 16.714445114135742,
|
| 424 |
+
"learning_rate": 1.2920634920634922e-05,
|
| 425 |
+
"loss": 0.3654,
|
| 426 |
+
"step": 2900
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.800976800976801,
|
| 430 |
+
"grad_norm": 27.8351993560791,
|
| 431 |
+
"learning_rate": 1.2798534798534798e-05,
|
| 432 |
+
"loss": 0.4181,
|
| 433 |
+
"step": 2950
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.8315018315018317,
|
| 437 |
+
"grad_norm": 4.469764709472656,
|
| 438 |
+
"learning_rate": 1.2676434676434676e-05,
|
| 439 |
+
"loss": 0.3711,
|
| 440 |
+
"step": 3000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.862026862026862,
|
| 444 |
+
"grad_norm": 65.09400939941406,
|
| 445 |
+
"learning_rate": 1.2554334554334555e-05,
|
| 446 |
+
"loss": 0.4071,
|
| 447 |
+
"step": 3050
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.8925518925518925,
|
| 451 |
+
"grad_norm": 17.013628005981445,
|
| 452 |
+
"learning_rate": 1.2432234432234434e-05,
|
| 453 |
+
"loss": 0.376,
|
| 454 |
+
"step": 3100
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.9230769230769231,
|
| 458 |
+
"grad_norm": 15.664719581604004,
|
| 459 |
+
"learning_rate": 1.2310134310134313e-05,
|
| 460 |
+
"loss": 0.4217,
|
| 461 |
+
"step": 3150
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.9536019536019538,
|
| 465 |
+
"grad_norm": 17.986469268798828,
|
| 466 |
+
"learning_rate": 1.218803418803419e-05,
|
| 467 |
+
"loss": 0.3626,
|
| 468 |
+
"step": 3200
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.9841269841269842,
|
| 472 |
+
"grad_norm": 14.723675727844238,
|
| 473 |
+
"learning_rate": 1.2065934065934067e-05,
|
| 474 |
+
"loss": 0.4065,
|
| 475 |
+
"step": 3250
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.0,
|
| 479 |
+
"eval_accuracy": 0.8335046248715313,
|
| 480 |
+
"eval_f1": 0.8335046248715313,
|
| 481 |
+
"eval_loss": 0.39165642857551575,
|
| 482 |
+
"eval_runtime": 3.4232,
|
| 483 |
+
"eval_samples_per_second": 284.237,
|
| 484 |
+
"eval_steps_per_second": 17.82,
|
| 485 |
+
"step": 3276
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.0146520146520146,
|
| 489 |
+
"grad_norm": 11.310654640197754,
|
| 490 |
+
"learning_rate": 1.1943833943833945e-05,
|
| 491 |
+
"loss": 0.4243,
|
| 492 |
+
"step": 3300
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.045177045177045,
|
| 496 |
+
"grad_norm": 26.5709228515625,
|
| 497 |
+
"learning_rate": 1.1821733821733822e-05,
|
| 498 |
+
"loss": 0.4102,
|
| 499 |
+
"step": 3350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.075702075702076,
|
| 503 |
+
"grad_norm": 9.054444313049316,
|
| 504 |
+
"learning_rate": 1.1699633699633701e-05,
|
| 505 |
+
"loss": 0.3512,
|
| 506 |
+
"step": 3400
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.1062271062271063,
|
| 510 |
+
"grad_norm": 29.050796508789062,
|
| 511 |
+
"learning_rate": 1.157753357753358e-05,
|
| 512 |
+
"loss": 0.3907,
|
| 513 |
+
"step": 3450
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.1367521367521367,
|
| 517 |
+
"grad_norm": 46.302555084228516,
|
| 518 |
+
"learning_rate": 1.1455433455433455e-05,
|
| 519 |
+
"loss": 0.3831,
|
| 520 |
+
"step": 3500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.167277167277167,
|
| 524 |
+
"grad_norm": 3.2793078422546387,
|
| 525 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 526 |
+
"loss": 0.3318,
|
| 527 |
+
"step": 3550
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.197802197802198,
|
| 531 |
+
"grad_norm": 3.5271809101104736,
|
| 532 |
+
"learning_rate": 1.1211233211233213e-05,
|
| 533 |
+
"loss": 0.4014,
|
| 534 |
+
"step": 3600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.2283272283272284,
|
| 538 |
+
"grad_norm": 28.36669921875,
|
| 539 |
+
"learning_rate": 1.1089133089133091e-05,
|
| 540 |
+
"loss": 0.298,
|
| 541 |
+
"step": 3650
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.258852258852259,
|
| 545 |
+
"grad_norm": 16.253847122192383,
|
| 546 |
+
"learning_rate": 1.0967032967032968e-05,
|
| 547 |
+
"loss": 0.3707,
|
| 548 |
+
"step": 3700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.2893772893772892,
|
| 552 |
+
"grad_norm": 33.73545455932617,
|
| 553 |
+
"learning_rate": 1.0844932844932845e-05,
|
| 554 |
+
"loss": 0.407,
|
| 555 |
+
"step": 3750
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.3199023199023197,
|
| 559 |
+
"grad_norm": 7.105137825012207,
|
| 560 |
+
"learning_rate": 1.0722832722832724e-05,
|
| 561 |
+
"loss": 0.3712,
|
| 562 |
+
"step": 3800
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.3504273504273505,
|
| 566 |
+
"grad_norm": 16.38484764099121,
|
| 567 |
+
"learning_rate": 1.0600732600732601e-05,
|
| 568 |
+
"loss": 0.358,
|
| 569 |
+
"step": 3850
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.380952380952381,
|
| 573 |
+
"grad_norm": 12.821770668029785,
|
| 574 |
+
"learning_rate": 1.047863247863248e-05,
|
| 575 |
+
"loss": 0.3807,
|
| 576 |
+
"step": 3900
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.4114774114774113,
|
| 580 |
+
"grad_norm": 13.208888053894043,
|
| 581 |
+
"learning_rate": 1.0356532356532358e-05,
|
| 582 |
+
"loss": 0.3175,
|
| 583 |
+
"step": 3950
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.442002442002442,
|
| 587 |
+
"grad_norm": 3.4101309776306152,
|
| 588 |
+
"learning_rate": 1.0234432234432234e-05,
|
| 589 |
+
"loss": 0.3779,
|
| 590 |
+
"step": 4000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.4725274725274726,
|
| 594 |
+
"grad_norm": 12.744550704956055,
|
| 595 |
+
"learning_rate": 1.0112332112332112e-05,
|
| 596 |
+
"loss": 0.3315,
|
| 597 |
+
"step": 4050
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.503052503052503,
|
| 601 |
+
"grad_norm": 30.4759464263916,
|
| 602 |
+
"learning_rate": 9.990231990231991e-06,
|
| 603 |
+
"loss": 0.2839,
|
| 604 |
+
"step": 4100
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.5335775335775335,
|
| 608 |
+
"grad_norm": 30.9493408203125,
|
| 609 |
+
"learning_rate": 9.86813186813187e-06,
|
| 610 |
+
"loss": 0.4101,
|
| 611 |
+
"step": 4150
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.564102564102564,
|
| 615 |
+
"grad_norm": 32.25123596191406,
|
| 616 |
+
"learning_rate": 9.746031746031747e-06,
|
| 617 |
+
"loss": 0.3538,
|
| 618 |
+
"step": 4200
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.5946275946275947,
|
| 622 |
+
"grad_norm": 23.044126510620117,
|
| 623 |
+
"learning_rate": 9.623931623931626e-06,
|
| 624 |
+
"loss": 0.3916,
|
| 625 |
+
"step": 4250
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.625152625152625,
|
| 629 |
+
"grad_norm": 12.858752250671387,
|
| 630 |
+
"learning_rate": 9.501831501831503e-06,
|
| 631 |
+
"loss": 0.3543,
|
| 632 |
+
"step": 4300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.6556776556776556,
|
| 636 |
+
"grad_norm": 13.903925895690918,
|
| 637 |
+
"learning_rate": 9.37973137973138e-06,
|
| 638 |
+
"loss": 0.3419,
|
| 639 |
+
"step": 4350
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.6862026862026864,
|
| 643 |
+
"grad_norm": 19.525449752807617,
|
| 644 |
+
"learning_rate": 9.257631257631258e-06,
|
| 645 |
+
"loss": 0.3833,
|
| 646 |
+
"step": 4400
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.716727716727717,
|
| 650 |
+
"grad_norm": 77.14259338378906,
|
| 651 |
+
"learning_rate": 9.135531135531135e-06,
|
| 652 |
+
"loss": 0.3502,
|
| 653 |
+
"step": 4450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.7472527472527473,
|
| 657 |
+
"grad_norm": 53.06977462768555,
|
| 658 |
+
"learning_rate": 9.013431013431014e-06,
|
| 659 |
+
"loss": 0.3557,
|
| 660 |
+
"step": 4500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.7777777777777777,
|
| 664 |
+
"grad_norm": 1.970027208328247,
|
| 665 |
+
"learning_rate": 8.891330891330891e-06,
|
| 666 |
+
"loss": 0.3539,
|
| 667 |
+
"step": 4550
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.808302808302808,
|
| 671 |
+
"grad_norm": 11.040838241577148,
|
| 672 |
+
"learning_rate": 8.76923076923077e-06,
|
| 673 |
+
"loss": 0.4407,
|
| 674 |
+
"step": 4600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.838827838827839,
|
| 678 |
+
"grad_norm": 3.146773099899292,
|
| 679 |
+
"learning_rate": 8.647130647130649e-06,
|
| 680 |
+
"loss": 0.3162,
|
| 681 |
+
"step": 4650
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.8693528693528694,
|
| 685 |
+
"grad_norm": 8.109123229980469,
|
| 686 |
+
"learning_rate": 8.525030525030526e-06,
|
| 687 |
+
"loss": 0.3643,
|
| 688 |
+
"step": 4700
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.8998778998779,
|
| 692 |
+
"grad_norm": 45.884132385253906,
|
| 693 |
+
"learning_rate": 8.402930402930404e-06,
|
| 694 |
+
"loss": 0.3473,
|
| 695 |
+
"step": 4750
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.9304029304029307,
|
| 699 |
+
"grad_norm": 45.499881744384766,
|
| 700 |
+
"learning_rate": 8.280830280830281e-06,
|
| 701 |
+
"loss": 0.3432,
|
| 702 |
+
"step": 4800
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.960927960927961,
|
| 706 |
+
"grad_norm": 8.839730262756348,
|
| 707 |
+
"learning_rate": 8.15873015873016e-06,
|
| 708 |
+
"loss": 0.4356,
|
| 709 |
+
"step": 4850
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.9914529914529915,
|
| 713 |
+
"grad_norm": 16.1923770904541,
|
| 714 |
+
"learning_rate": 8.036630036630037e-06,
|
| 715 |
+
"loss": 0.3048,
|
| 716 |
+
"step": 4900
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.0,
|
| 720 |
+
"eval_accuracy": 0.841726618705036,
|
| 721 |
+
"eval_f1": 0.842039749114194,
|
| 722 |
+
"eval_loss": 0.4310351014137268,
|
| 723 |
+
"eval_runtime": 3.4121,
|
| 724 |
+
"eval_samples_per_second": 285.165,
|
| 725 |
+
"eval_steps_per_second": 17.878,
|
| 726 |
+
"step": 4914
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 3.021978021978022,
|
| 730 |
+
"grad_norm": 0.17316707968711853,
|
| 731 |
+
"learning_rate": 7.914529914529914e-06,
|
| 732 |
+
"loss": 0.3123,
|
| 733 |
+
"step": 4950
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 3.0525030525030523,
|
| 737 |
+
"grad_norm": 34.99089050292969,
|
| 738 |
+
"learning_rate": 7.792429792429793e-06,
|
| 739 |
+
"loss": 0.2688,
|
| 740 |
+
"step": 5000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.083028083028083,
|
| 744 |
+
"grad_norm": 33.27500534057617,
|
| 745 |
+
"learning_rate": 7.670329670329671e-06,
|
| 746 |
+
"loss": 0.3351,
|
| 747 |
+
"step": 5050
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.1135531135531136,
|
| 751 |
+
"grad_norm": 1.5347567796707153,
|
| 752 |
+
"learning_rate": 7.5482295482295485e-06,
|
| 753 |
+
"loss": 0.2936,
|
| 754 |
+
"step": 5100
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 3.144078144078144,
|
| 758 |
+
"grad_norm": 41.4924430847168,
|
| 759 |
+
"learning_rate": 7.426129426129427e-06,
|
| 760 |
+
"loss": 0.3149,
|
| 761 |
+
"step": 5150
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.1746031746031744,
|
| 765 |
+
"grad_norm": 11.000214576721191,
|
| 766 |
+
"learning_rate": 7.304029304029304e-06,
|
| 767 |
+
"loss": 0.3578,
|
| 768 |
+
"step": 5200
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.2051282051282053,
|
| 772 |
+
"grad_norm": 44.290706634521484,
|
| 773 |
+
"learning_rate": 7.181929181929183e-06,
|
| 774 |
+
"loss": 0.3072,
|
| 775 |
+
"step": 5250
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 3.2356532356532357,
|
| 779 |
+
"grad_norm": 15.626100540161133,
|
| 780 |
+
"learning_rate": 7.059829059829061e-06,
|
| 781 |
+
"loss": 0.3477,
|
| 782 |
+
"step": 5300
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.266178266178266,
|
| 786 |
+
"grad_norm": 19.285181045532227,
|
| 787 |
+
"learning_rate": 6.937728937728938e-06,
|
| 788 |
+
"loss": 0.3064,
|
| 789 |
+
"step": 5350
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.2967032967032965,
|
| 793 |
+
"grad_norm": 44.707035064697266,
|
| 794 |
+
"learning_rate": 6.8156288156288165e-06,
|
| 795 |
+
"loss": 0.3293,
|
| 796 |
+
"step": 5400
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 3.3272283272283274,
|
| 800 |
+
"grad_norm": 0.5621269345283508,
|
| 801 |
+
"learning_rate": 6.6935286935286936e-06,
|
| 802 |
+
"loss": 0.2655,
|
| 803 |
+
"step": 5450
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.357753357753358,
|
| 807 |
+
"grad_norm": 44.706912994384766,
|
| 808 |
+
"learning_rate": 6.571428571428572e-06,
|
| 809 |
+
"loss": 0.3088,
|
| 810 |
+
"step": 5500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.3882783882783882,
|
| 814 |
+
"grad_norm": 39.22804641723633,
|
| 815 |
+
"learning_rate": 6.44932844932845e-06,
|
| 816 |
+
"loss": 0.3369,
|
| 817 |
+
"step": 5550
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 3.4188034188034186,
|
| 821 |
+
"grad_norm": 22.248640060424805,
|
| 822 |
+
"learning_rate": 6.327228327228327e-06,
|
| 823 |
+
"loss": 0.2965,
|
| 824 |
+
"step": 5600
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.4493284493284495,
|
| 828 |
+
"grad_norm": 20.197702407836914,
|
| 829 |
+
"learning_rate": 6.205128205128206e-06,
|
| 830 |
+
"loss": 0.3755,
|
| 831 |
+
"step": 5650
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.47985347985348,
|
| 835 |
+
"grad_norm": 48.2933349609375,
|
| 836 |
+
"learning_rate": 6.083028083028083e-06,
|
| 837 |
+
"loss": 0.3001,
|
| 838 |
+
"step": 5700
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 3.5103785103785103,
|
| 842 |
+
"grad_norm": 44.70425796508789,
|
| 843 |
+
"learning_rate": 5.960927960927962e-06,
|
| 844 |
+
"loss": 0.3492,
|
| 845 |
+
"step": 5750
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.5409035409035408,
|
| 849 |
+
"grad_norm": 52.380699157714844,
|
| 850 |
+
"learning_rate": 5.8388278388278395e-06,
|
| 851 |
+
"loss": 0.3542,
|
| 852 |
+
"step": 5800
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 3.571428571428571,
|
| 856 |
+
"grad_norm": 61.83149337768555,
|
| 857 |
+
"learning_rate": 5.7167277167277165e-06,
|
| 858 |
+
"loss": 0.4119,
|
| 859 |
+
"step": 5850
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.601953601953602,
|
| 863 |
+
"grad_norm": 57.2952766418457,
|
| 864 |
+
"learning_rate": 5.594627594627595e-06,
|
| 865 |
+
"loss": 0.2609,
|
| 866 |
+
"step": 5900
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.6324786324786325,
|
| 870 |
+
"grad_norm": 9.41811466217041,
|
| 871 |
+
"learning_rate": 5.472527472527474e-06,
|
| 872 |
+
"loss": 0.2455,
|
| 873 |
+
"step": 5950
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.663003663003663,
|
| 877 |
+
"grad_norm": 21.504688262939453,
|
| 878 |
+
"learning_rate": 5.350427350427351e-06,
|
| 879 |
+
"loss": 0.2937,
|
| 880 |
+
"step": 6000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.6935286935286937,
|
| 884 |
+
"grad_norm": 21.507137298583984,
|
| 885 |
+
"learning_rate": 5.228327228327229e-06,
|
| 886 |
+
"loss": 0.3562,
|
| 887 |
+
"step": 6050
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 3.724053724053724,
|
| 891 |
+
"grad_norm": 27.680004119873047,
|
| 892 |
+
"learning_rate": 5.106227106227107e-06,
|
| 893 |
+
"loss": 0.3818,
|
| 894 |
+
"step": 6100
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 3.7545787545787546,
|
| 898 |
+
"grad_norm": 3.6276087760925293,
|
| 899 |
+
"learning_rate": 4.9841269841269845e-06,
|
| 900 |
+
"loss": 0.3531,
|
| 901 |
+
"step": 6150
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.785103785103785,
|
| 905 |
+
"grad_norm": 7.672877311706543,
|
| 906 |
+
"learning_rate": 4.862026862026862e-06,
|
| 907 |
+
"loss": 0.3249,
|
| 908 |
+
"step": 6200
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.8156288156288154,
|
| 912 |
+
"grad_norm": 4.853017330169678,
|
| 913 |
+
"learning_rate": 4.73992673992674e-06,
|
| 914 |
+
"loss": 0.3108,
|
| 915 |
+
"step": 6250
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 3.8461538461538463,
|
| 919 |
+
"grad_norm": 5.495295524597168,
|
| 920 |
+
"learning_rate": 4.617826617826618e-06,
|
| 921 |
+
"loss": 0.2307,
|
| 922 |
+
"step": 6300
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 3.8766788766788767,
|
| 926 |
+
"grad_norm": 8.944286346435547,
|
| 927 |
+
"learning_rate": 4.495726495726496e-06,
|
| 928 |
+
"loss": 0.3389,
|
| 929 |
+
"step": 6350
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 3.907203907203907,
|
| 933 |
+
"grad_norm": 50.722347259521484,
|
| 934 |
+
"learning_rate": 4.373626373626374e-06,
|
| 935 |
+
"loss": 0.3585,
|
| 936 |
+
"step": 6400
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 3.937728937728938,
|
| 940 |
+
"grad_norm": 1.0614252090454102,
|
| 941 |
+
"learning_rate": 4.251526251526252e-06,
|
| 942 |
+
"loss": 0.2608,
|
| 943 |
+
"step": 6450
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 3.9682539682539684,
|
| 947 |
+
"grad_norm": 26.249635696411133,
|
| 948 |
+
"learning_rate": 4.12942612942613e-06,
|
| 949 |
+
"loss": 0.2843,
|
| 950 |
+
"step": 6500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.998778998778999,
|
| 954 |
+
"grad_norm": 46.925880432128906,
|
| 955 |
+
"learning_rate": 4.0073260073260075e-06,
|
| 956 |
+
"loss": 0.3267,
|
| 957 |
+
"step": 6550
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 4.0,
|
| 961 |
+
"eval_accuracy": 0.8252826310380267,
|
| 962 |
+
"eval_f1": 0.8320719787613731,
|
| 963 |
+
"eval_loss": 0.61274653673172,
|
| 964 |
+
"eval_runtime": 3.415,
|
| 965 |
+
"eval_samples_per_second": 284.919,
|
| 966 |
+
"eval_steps_per_second": 17.862,
|
| 967 |
+
"step": 6552
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 4.029304029304029,
|
| 971 |
+
"grad_norm": 6.32822847366333,
|
| 972 |
+
"learning_rate": 3.885225885225885e-06,
|
| 973 |
+
"loss": 0.2132,
|
| 974 |
+
"step": 6600
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.05982905982906,
|
| 978 |
+
"grad_norm": 36.05378341674805,
|
| 979 |
+
"learning_rate": 3.763125763125763e-06,
|
| 980 |
+
"loss": 0.2523,
|
| 981 |
+
"step": 6650
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 4.09035409035409,
|
| 985 |
+
"grad_norm": 0.1818905770778656,
|
| 986 |
+
"learning_rate": 3.641025641025641e-06,
|
| 987 |
+
"loss": 0.2759,
|
| 988 |
+
"step": 6700
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 4.1208791208791204,
|
| 992 |
+
"grad_norm": 1.4091908931732178,
|
| 993 |
+
"learning_rate": 3.5189255189255194e-06,
|
| 994 |
+
"loss": 0.2485,
|
| 995 |
+
"step": 6750
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 4.151404151404152,
|
| 999 |
+
"grad_norm": 124.52008056640625,
|
| 1000 |
+
"learning_rate": 3.3968253968253972e-06,
|
| 1001 |
+
"loss": 0.2202,
|
| 1002 |
+
"step": 6800
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 4.181929181929182,
|
| 1006 |
+
"grad_norm": 28.67030143737793,
|
| 1007 |
+
"learning_rate": 3.274725274725275e-06,
|
| 1008 |
+
"loss": 0.328,
|
| 1009 |
+
"step": 6850
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 4.212454212454213,
|
| 1013 |
+
"grad_norm": 53.90391159057617,
|
| 1014 |
+
"learning_rate": 3.152625152625153e-06,
|
| 1015 |
+
"loss": 0.3406,
|
| 1016 |
+
"step": 6900
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 4.242979242979243,
|
| 1020 |
+
"grad_norm": 0.3543091118335724,
|
| 1021 |
+
"learning_rate": 3.0305250305250304e-06,
|
| 1022 |
+
"loss": 0.2255,
|
| 1023 |
+
"step": 6950
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 4.273504273504273,
|
| 1027 |
+
"grad_norm": 5.9171319007873535,
|
| 1028 |
+
"learning_rate": 2.9084249084249087e-06,
|
| 1029 |
+
"loss": 0.1897,
|
| 1030 |
+
"step": 7000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 4.304029304029304,
|
| 1034 |
+
"grad_norm": 121.3272705078125,
|
| 1035 |
+
"learning_rate": 2.7863247863247866e-06,
|
| 1036 |
+
"loss": 0.2379,
|
| 1037 |
+
"step": 7050
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 4.334554334554334,
|
| 1041 |
+
"grad_norm": 29.23149299621582,
|
| 1042 |
+
"learning_rate": 2.6642246642246644e-06,
|
| 1043 |
+
"loss": 0.2746,
|
| 1044 |
+
"step": 7100
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 4.365079365079365,
|
| 1048 |
+
"grad_norm": 0.29333066940307617,
|
| 1049 |
+
"learning_rate": 2.5421245421245423e-06,
|
| 1050 |
+
"loss": 0.235,
|
| 1051 |
+
"step": 7150
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 4.395604395604396,
|
| 1055 |
+
"grad_norm": 0.5657308101654053,
|
| 1056 |
+
"learning_rate": 2.42002442002442e-06,
|
| 1057 |
+
"loss": 0.2173,
|
| 1058 |
+
"step": 7200
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.426129426129426,
|
| 1062 |
+
"grad_norm": 65.32083129882812,
|
| 1063 |
+
"learning_rate": 2.297924297924298e-06,
|
| 1064 |
+
"loss": 0.2274,
|
| 1065 |
+
"step": 7250
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.456654456654457,
|
| 1069 |
+
"grad_norm": 46.64541244506836,
|
| 1070 |
+
"learning_rate": 2.175824175824176e-06,
|
| 1071 |
+
"loss": 0.2169,
|
| 1072 |
+
"step": 7300
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.487179487179487,
|
| 1076 |
+
"grad_norm": 33.644920349121094,
|
| 1077 |
+
"learning_rate": 2.0537240537240538e-06,
|
| 1078 |
+
"loss": 0.3825,
|
| 1079 |
+
"step": 7350
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 4.517704517704518,
|
| 1083 |
+
"grad_norm": 0.12038320302963257,
|
| 1084 |
+
"learning_rate": 1.931623931623932e-06,
|
| 1085 |
+
"loss": 0.2777,
|
| 1086 |
+
"step": 7400
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 4.548229548229548,
|
| 1090 |
+
"grad_norm": 0.2744602560997009,
|
| 1091 |
+
"learning_rate": 1.8095238095238097e-06,
|
| 1092 |
+
"loss": 0.2477,
|
| 1093 |
+
"step": 7450
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 4.5787545787545785,
|
| 1097 |
+
"grad_norm": 6.675881385803223,
|
| 1098 |
+
"learning_rate": 1.6874236874236878e-06,
|
| 1099 |
+
"loss": 0.2935,
|
| 1100 |
+
"step": 7500
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 4.609279609279609,
|
| 1104 |
+
"grad_norm": 0.19729621708393097,
|
| 1105 |
+
"learning_rate": 1.5653235653235654e-06,
|
| 1106 |
+
"loss": 0.2718,
|
| 1107 |
+
"step": 7550
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 4.639804639804639,
|
| 1111 |
+
"grad_norm": 10.316431045532227,
|
| 1112 |
+
"learning_rate": 1.4432234432234433e-06,
|
| 1113 |
+
"loss": 0.2216,
|
| 1114 |
+
"step": 7600
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 4.670329670329671,
|
| 1118 |
+
"grad_norm": 0.23969869315624237,
|
| 1119 |
+
"learning_rate": 1.3211233211233212e-06,
|
| 1120 |
+
"loss": 0.3216,
|
| 1121 |
+
"step": 7650
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 4.700854700854701,
|
| 1125 |
+
"grad_norm": 19.417451858520508,
|
| 1126 |
+
"learning_rate": 1.1990231990231992e-06,
|
| 1127 |
+
"loss": 0.308,
|
| 1128 |
+
"step": 7700
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 4.7313797313797314,
|
| 1132 |
+
"grad_norm": 3.6119327545166016,
|
| 1133 |
+
"learning_rate": 1.076923076923077e-06,
|
| 1134 |
+
"loss": 0.2515,
|
| 1135 |
+
"step": 7750
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 4.761904761904762,
|
| 1139 |
+
"grad_norm": 0.5512221455574036,
|
| 1140 |
+
"learning_rate": 9.548229548229548e-07,
|
| 1141 |
+
"loss": 0.2688,
|
| 1142 |
+
"step": 7800
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.792429792429792,
|
| 1146 |
+
"grad_norm": 1.3888872861862183,
|
| 1147 |
+
"learning_rate": 8.327228327228327e-07,
|
| 1148 |
+
"loss": 0.2449,
|
| 1149 |
+
"step": 7850
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 4.822954822954823,
|
| 1153 |
+
"grad_norm": 34.30708312988281,
|
| 1154 |
+
"learning_rate": 7.106227106227107e-07,
|
| 1155 |
+
"loss": 0.2926,
|
| 1156 |
+
"step": 7900
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 4.853479853479853,
|
| 1160 |
+
"grad_norm": 7.761233806610107,
|
| 1161 |
+
"learning_rate": 5.885225885225886e-07,
|
| 1162 |
+
"loss": 0.3384,
|
| 1163 |
+
"step": 7950
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 4.884004884004884,
|
| 1167 |
+
"grad_norm": 67.32460021972656,
|
| 1168 |
+
"learning_rate": 4.664224664224665e-07,
|
| 1169 |
+
"loss": 0.2586,
|
| 1170 |
+
"step": 8000
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 4.914529914529915,
|
| 1174 |
+
"grad_norm": 0.2525177299976349,
|
| 1175 |
+
"learning_rate": 3.4432234432234435e-07,
|
| 1176 |
+
"loss": 0.3106,
|
| 1177 |
+
"step": 8050
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.945054945054945,
|
| 1181 |
+
"grad_norm": 31.685503005981445,
|
| 1182 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 1183 |
+
"loss": 0.277,
|
| 1184 |
+
"step": 8100
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.975579975579976,
|
| 1188 |
+
"grad_norm": 13.309945106506348,
|
| 1189 |
+
"learning_rate": 1.0012210012210014e-07,
|
| 1190 |
+
"loss": 0.286,
|
| 1191 |
+
"step": 8150
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 5.0,
|
| 1195 |
+
"eval_accuracy": 0.8458376156217883,
|
| 1196 |
+
"eval_f1": 0.847602022392802,
|
| 1197 |
+
"eval_loss": 0.6701350808143616,
|
| 1198 |
+
"eval_runtime": 3.429,
|
| 1199 |
+
"eval_samples_per_second": 283.76,
|
| 1200 |
+
"eval_steps_per_second": 17.79,
|
| 1201 |
+
"step": 8190
|
| 1202 |
+
}
|
| 1203 |
+
],
|
| 1204 |
+
"logging_steps": 50,
|
| 1205 |
+
"max_steps": 8190,
|
| 1206 |
+
"num_input_tokens_seen": 0,
|
| 1207 |
+
"num_train_epochs": 5,
|
| 1208 |
+
"save_steps": 500,
|
| 1209 |
+
"stateful_callbacks": {
|
| 1210 |
+
"TrainerControl": {
|
| 1211 |
+
"args": {
|
| 1212 |
+
"should_epoch_stop": false,
|
| 1213 |
+
"should_evaluate": false,
|
| 1214 |
+
"should_log": false,
|
| 1215 |
+
"should_save": true,
|
| 1216 |
+
"should_training_stop": true
|
| 1217 |
+
},
|
| 1218 |
+
"attributes": {}
|
| 1219 |
+
}
|
| 1220 |
+
},
|
| 1221 |
+
"total_flos": 4309101309158400.0,
|
| 1222 |
+
"train_batch_size": 8,
|
| 1223 |
+
"trial_name": null,
|
| 1224 |
+
"trial_params": null
|
| 1225 |
+
}
|
xlmr_hope_ml/checkpoint-8190/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c82fed9c3ff70f7c941da76fd2069a4d27a53f3fc0a11157cf37f02fe0dfd54e
|
| 3 |
+
size 5841
|