Upload folder using huggingface_hub
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2735 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.33.3",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f35f92e2f2695f86c3d2e2fac860510097e2e0463c2adf9b9ac153c713bebee
|
| 3 |
+
size 668114693
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:809c06c3a4f2eb006554c2b3f7ceb8c424e73896d4c8a33109361411b7acbeab
|
| 3 |
+
size 494001725
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9d25c0ffcca6377887e0a5a7ef01dbbf757e782c40f96ca3e1f4f8f2f31ae3c
|
| 3 |
+
size 13617
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3efbd351a1b71f515f4fabc051f58d98a233acb87f129553364c618093e42b85
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2735 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.218982703597179,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 112640,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4.9917917602406e-05,
|
| 14 |
+
"loss": 9.4912,
|
| 15 |
+
"step": 250
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4.9835835204812e-05,
|
| 20 |
+
"loss": 9.0253,
|
| 21 |
+
"step": 500
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 4.9753752807218e-05,
|
| 26 |
+
"loss": 8.889,
|
| 27 |
+
"step": 750
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 4.9671670409624e-05,
|
| 32 |
+
"loss": 8.7297,
|
| 33 |
+
"step": 1000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 4.958958801203e-05,
|
| 38 |
+
"loss": 8.6079,
|
| 39 |
+
"step": 1250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 4.9507505614436e-05,
|
| 44 |
+
"loss": 8.525,
|
| 45 |
+
"step": 1500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 4.9425423216842e-05,
|
| 50 |
+
"loss": 8.4223,
|
| 51 |
+
"step": 1750
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 4.9343340819248e-05,
|
| 56 |
+
"loss": 8.3692,
|
| 57 |
+
"step": 2000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 4.926125842165399e-05,
|
| 62 |
+
"loss": 8.332,
|
| 63 |
+
"step": 2250
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 4.917917602406e-05,
|
| 68 |
+
"loss": 8.2672,
|
| 69 |
+
"step": 2500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 4.9097093626466e-05,
|
| 74 |
+
"loss": 8.1887,
|
| 75 |
+
"step": 2750
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 4.9015011228871996e-05,
|
| 80 |
+
"loss": 8.1799,
|
| 81 |
+
"step": 3000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 4.893292883127799e-05,
|
| 86 |
+
"loss": 8.1428,
|
| 87 |
+
"step": 3250
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 4.8850846433683995e-05,
|
| 92 |
+
"loss": 8.1542,
|
| 93 |
+
"step": 3500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 4.8768764036089995e-05,
|
| 98 |
+
"loss": 8.0947,
|
| 99 |
+
"step": 3750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 4.868668163849599e-05,
|
| 104 |
+
"loss": 8.0386,
|
| 105 |
+
"step": 4000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 4.860459924090199e-05,
|
| 110 |
+
"loss": 7.9978,
|
| 111 |
+
"step": 4250
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 4.852251684330799e-05,
|
| 116 |
+
"loss": 7.9489,
|
| 117 |
+
"step": 4500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 4.8440434445713986e-05,
|
| 122 |
+
"loss": 7.9363,
|
| 123 |
+
"step": 4750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 4.8358352048119985e-05,
|
| 128 |
+
"loss": 7.9265,
|
| 129 |
+
"step": 5000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 4.8276269650525985e-05,
|
| 134 |
+
"loss": 7.9027,
|
| 135 |
+
"step": 5250
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11,
|
| 139 |
+
"learning_rate": 4.819418725293199e-05,
|
| 140 |
+
"loss": 7.8451,
|
| 141 |
+
"step": 5500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 4.8112104855337984e-05,
|
| 146 |
+
"loss": 7.7337,
|
| 147 |
+
"step": 5750
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.12,
|
| 151 |
+
"learning_rate": 4.8030022457743983e-05,
|
| 152 |
+
"loss": 7.7837,
|
| 153 |
+
"step": 6000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 4.794794006014998e-05,
|
| 158 |
+
"loss": 7.7527,
|
| 159 |
+
"step": 6250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.13,
|
| 163 |
+
"learning_rate": 4.786585766255598e-05,
|
| 164 |
+
"loss": 7.7434,
|
| 165 |
+
"step": 6500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.13,
|
| 169 |
+
"learning_rate": 4.778377526496198e-05,
|
| 170 |
+
"loss": 7.6981,
|
| 171 |
+
"step": 6750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14,
|
| 175 |
+
"learning_rate": 4.770169286736798e-05,
|
| 176 |
+
"loss": 7.6708,
|
| 177 |
+
"step": 7000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.14,
|
| 181 |
+
"learning_rate": 4.761961046977398e-05,
|
| 182 |
+
"loss": 7.5951,
|
| 183 |
+
"step": 7250
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.15,
|
| 187 |
+
"learning_rate": 4.753752807217998e-05,
|
| 188 |
+
"loss": 7.5975,
|
| 189 |
+
"step": 7500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.15,
|
| 193 |
+
"learning_rate": 4.745544567458598e-05,
|
| 194 |
+
"loss": 7.5186,
|
| 195 |
+
"step": 7750
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.16,
|
| 199 |
+
"learning_rate": 4.737336327699198e-05,
|
| 200 |
+
"loss": 7.4844,
|
| 201 |
+
"step": 8000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.16,
|
| 205 |
+
"learning_rate": 4.729128087939798e-05,
|
| 206 |
+
"loss": 7.4021,
|
| 207 |
+
"step": 8250
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.17,
|
| 211 |
+
"learning_rate": 4.720919848180398e-05,
|
| 212 |
+
"loss": 7.4089,
|
| 213 |
+
"step": 8500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.17,
|
| 217 |
+
"learning_rate": 4.712711608420998e-05,
|
| 218 |
+
"loss": 7.3132,
|
| 219 |
+
"step": 8750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.18,
|
| 223 |
+
"learning_rate": 4.704503368661598e-05,
|
| 224 |
+
"loss": 7.3552,
|
| 225 |
+
"step": 9000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.18,
|
| 229 |
+
"learning_rate": 4.696295128902197e-05,
|
| 230 |
+
"loss": 7.3327,
|
| 231 |
+
"step": 9250
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.19,
|
| 235 |
+
"learning_rate": 4.6880868891427976e-05,
|
| 236 |
+
"loss": 7.2294,
|
| 237 |
+
"step": 9500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.19,
|
| 241 |
+
"learning_rate": 4.6798786493833976e-05,
|
| 242 |
+
"loss": 7.2296,
|
| 243 |
+
"step": 9750
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.2,
|
| 247 |
+
"learning_rate": 4.671670409623997e-05,
|
| 248 |
+
"loss": 7.1595,
|
| 249 |
+
"step": 10000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.2,
|
| 253 |
+
"learning_rate": 4.663462169864597e-05,
|
| 254 |
+
"loss": 7.1434,
|
| 255 |
+
"step": 10250
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.21,
|
| 259 |
+
"learning_rate": 4.6552539301051974e-05,
|
| 260 |
+
"loss": 7.1707,
|
| 261 |
+
"step": 10500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.21,
|
| 265 |
+
"learning_rate": 4.6470456903457974e-05,
|
| 266 |
+
"loss": 7.0756,
|
| 267 |
+
"step": 10750
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.22,
|
| 271 |
+
"learning_rate": 4.6388374505863967e-05,
|
| 272 |
+
"loss": 7.0205,
|
| 273 |
+
"step": 11000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.22,
|
| 277 |
+
"learning_rate": 4.6306292108269966e-05,
|
| 278 |
+
"loss": 7.0475,
|
| 279 |
+
"step": 11250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.23,
|
| 283 |
+
"learning_rate": 4.622420971067597e-05,
|
| 284 |
+
"loss": 7.0355,
|
| 285 |
+
"step": 11500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.23,
|
| 289 |
+
"learning_rate": 4.6142127313081965e-05,
|
| 290 |
+
"loss": 6.9695,
|
| 291 |
+
"step": 11750
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.24,
|
| 295 |
+
"learning_rate": 4.6060044915487965e-05,
|
| 296 |
+
"loss": 6.962,
|
| 297 |
+
"step": 12000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.24,
|
| 301 |
+
"learning_rate": 4.5977962517893964e-05,
|
| 302 |
+
"loss": 6.9281,
|
| 303 |
+
"step": 12250
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.25,
|
| 307 |
+
"learning_rate": 4.5895880120299964e-05,
|
| 308 |
+
"loss": 6.9421,
|
| 309 |
+
"step": 12500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.25,
|
| 313 |
+
"learning_rate": 4.581379772270596e-05,
|
| 314 |
+
"loss": 6.9498,
|
| 315 |
+
"step": 12750
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.26,
|
| 319 |
+
"learning_rate": 4.573171532511196e-05,
|
| 320 |
+
"loss": 6.8833,
|
| 321 |
+
"step": 13000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.26,
|
| 325 |
+
"learning_rate": 4.564963292751796e-05,
|
| 326 |
+
"loss": 6.8878,
|
| 327 |
+
"step": 13250
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.27,
|
| 331 |
+
"learning_rate": 4.556755052992396e-05,
|
| 332 |
+
"loss": 6.845,
|
| 333 |
+
"step": 13500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.27,
|
| 337 |
+
"learning_rate": 4.548546813232996e-05,
|
| 338 |
+
"loss": 6.833,
|
| 339 |
+
"step": 13750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.28,
|
| 343 |
+
"learning_rate": 4.540338573473596e-05,
|
| 344 |
+
"loss": 6.8062,
|
| 345 |
+
"step": 14000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.28,
|
| 349 |
+
"learning_rate": 4.532130333714196e-05,
|
| 350 |
+
"loss": 6.8126,
|
| 351 |
+
"step": 14250
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.29,
|
| 355 |
+
"learning_rate": 4.523922093954796e-05,
|
| 356 |
+
"loss": 6.7655,
|
| 357 |
+
"step": 14500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.29,
|
| 361 |
+
"learning_rate": 4.515713854195396e-05,
|
| 362 |
+
"loss": 6.7613,
|
| 363 |
+
"step": 14750
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.3,
|
| 367 |
+
"learning_rate": 4.507505614435996e-05,
|
| 368 |
+
"loss": 6.6869,
|
| 369 |
+
"step": 15000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.3,
|
| 373 |
+
"learning_rate": 4.499297374676595e-05,
|
| 374 |
+
"loss": 6.6834,
|
| 375 |
+
"step": 15250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.31,
|
| 379 |
+
"learning_rate": 4.491089134917196e-05,
|
| 380 |
+
"loss": 6.7371,
|
| 381 |
+
"step": 15500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.31,
|
| 385 |
+
"learning_rate": 4.482880895157796e-05,
|
| 386 |
+
"loss": 6.6962,
|
| 387 |
+
"step": 15750
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.32,
|
| 391 |
+
"learning_rate": 4.4746726553983956e-05,
|
| 392 |
+
"loss": 6.6554,
|
| 393 |
+
"step": 16000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.32,
|
| 397 |
+
"learning_rate": 4.466464415638995e-05,
|
| 398 |
+
"loss": 6.6898,
|
| 399 |
+
"step": 16250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.33,
|
| 403 |
+
"learning_rate": 4.4582561758795955e-05,
|
| 404 |
+
"loss": 6.6349,
|
| 405 |
+
"step": 16500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.33,
|
| 409 |
+
"learning_rate": 4.4500479361201955e-05,
|
| 410 |
+
"loss": 6.6075,
|
| 411 |
+
"step": 16750
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.33,
|
| 415 |
+
"learning_rate": 4.441839696360795e-05,
|
| 416 |
+
"loss": 6.6128,
|
| 417 |
+
"step": 17000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.34,
|
| 421 |
+
"learning_rate": 4.433631456601395e-05,
|
| 422 |
+
"loss": 6.5883,
|
| 423 |
+
"step": 17250
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.34,
|
| 427 |
+
"learning_rate": 4.4254232168419953e-05,
|
| 428 |
+
"loss": 6.5475,
|
| 429 |
+
"step": 17500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.35,
|
| 433 |
+
"learning_rate": 4.4172149770825946e-05,
|
| 434 |
+
"loss": 6.4996,
|
| 435 |
+
"step": 17750
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.35,
|
| 439 |
+
"learning_rate": 4.4090067373231946e-05,
|
| 440 |
+
"loss": 6.5243,
|
| 441 |
+
"step": 18000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.36,
|
| 445 |
+
"learning_rate": 4.4007984975637945e-05,
|
| 446 |
+
"loss": 6.5113,
|
| 447 |
+
"step": 18250
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.36,
|
| 451 |
+
"learning_rate": 4.392590257804395e-05,
|
| 452 |
+
"loss": 6.4859,
|
| 453 |
+
"step": 18500
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.37,
|
| 457 |
+
"learning_rate": 4.3843820180449944e-05,
|
| 458 |
+
"loss": 6.473,
|
| 459 |
+
"step": 18750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.37,
|
| 463 |
+
"learning_rate": 4.3761737782855944e-05,
|
| 464 |
+
"loss": 6.5033,
|
| 465 |
+
"step": 19000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.38,
|
| 469 |
+
"learning_rate": 4.367965538526194e-05,
|
| 470 |
+
"loss": 6.4411,
|
| 471 |
+
"step": 19250
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.38,
|
| 475 |
+
"learning_rate": 4.359757298766794e-05,
|
| 476 |
+
"loss": 6.4374,
|
| 477 |
+
"step": 19500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.39,
|
| 481 |
+
"learning_rate": 4.351549059007394e-05,
|
| 482 |
+
"loss": 6.4449,
|
| 483 |
+
"step": 19750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.39,
|
| 487 |
+
"learning_rate": 4.343340819247994e-05,
|
| 488 |
+
"loss": 6.4043,
|
| 489 |
+
"step": 20000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.4,
|
| 493 |
+
"learning_rate": 4.335132579488594e-05,
|
| 494 |
+
"loss": 6.3784,
|
| 495 |
+
"step": 20250
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.4,
|
| 499 |
+
"learning_rate": 4.326924339729194e-05,
|
| 500 |
+
"loss": 6.3888,
|
| 501 |
+
"step": 20500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.41,
|
| 505 |
+
"learning_rate": 4.318716099969794e-05,
|
| 506 |
+
"loss": 6.3818,
|
| 507 |
+
"step": 20750
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.41,
|
| 511 |
+
"learning_rate": 4.310507860210394e-05,
|
| 512 |
+
"loss": 6.3793,
|
| 513 |
+
"step": 21000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.42,
|
| 517 |
+
"learning_rate": 4.302299620450993e-05,
|
| 518 |
+
"loss": 6.3635,
|
| 519 |
+
"step": 21250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.42,
|
| 523 |
+
"learning_rate": 4.294091380691594e-05,
|
| 524 |
+
"loss": 6.3109,
|
| 525 |
+
"step": 21500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.43,
|
| 529 |
+
"learning_rate": 4.285883140932194e-05,
|
| 530 |
+
"loss": 6.3004,
|
| 531 |
+
"step": 21750
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.43,
|
| 535 |
+
"learning_rate": 4.277674901172794e-05,
|
| 536 |
+
"loss": 6.3036,
|
| 537 |
+
"step": 22000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.44,
|
| 541 |
+
"learning_rate": 4.269466661413393e-05,
|
| 542 |
+
"loss": 6.233,
|
| 543 |
+
"step": 22250
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.44,
|
| 547 |
+
"learning_rate": 4.2612584216539936e-05,
|
| 548 |
+
"loss": 6.242,
|
| 549 |
+
"step": 22500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.45,
|
| 553 |
+
"learning_rate": 4.2530501818945936e-05,
|
| 554 |
+
"loss": 6.2686,
|
| 555 |
+
"step": 22750
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.45,
|
| 559 |
+
"learning_rate": 4.244841942135193e-05,
|
| 560 |
+
"loss": 6.2183,
|
| 561 |
+
"step": 23000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.46,
|
| 565 |
+
"learning_rate": 4.236633702375793e-05,
|
| 566 |
+
"loss": 6.2428,
|
| 567 |
+
"step": 23250
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.46,
|
| 571 |
+
"learning_rate": 4.2284254626163934e-05,
|
| 572 |
+
"loss": 6.1933,
|
| 573 |
+
"step": 23500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.47,
|
| 577 |
+
"learning_rate": 4.2202172228569934e-05,
|
| 578 |
+
"loss": 6.1957,
|
| 579 |
+
"step": 23750
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.47,
|
| 583 |
+
"learning_rate": 4.212008983097593e-05,
|
| 584 |
+
"loss": 6.2449,
|
| 585 |
+
"step": 24000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.48,
|
| 589 |
+
"learning_rate": 4.2038007433381926e-05,
|
| 590 |
+
"loss": 6.186,
|
| 591 |
+
"step": 24250
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.48,
|
| 595 |
+
"learning_rate": 4.195592503578793e-05,
|
| 596 |
+
"loss": 6.1722,
|
| 597 |
+
"step": 24500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.49,
|
| 601 |
+
"learning_rate": 4.1873842638193925e-05,
|
| 602 |
+
"loss": 6.193,
|
| 603 |
+
"step": 24750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.49,
|
| 607 |
+
"learning_rate": 4.1791760240599925e-05,
|
| 608 |
+
"loss": 6.1829,
|
| 609 |
+
"step": 25000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.5,
|
| 613 |
+
"learning_rate": 4.1709677843005924e-05,
|
| 614 |
+
"loss": 6.1587,
|
| 615 |
+
"step": 25250
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.5,
|
| 619 |
+
"learning_rate": 4.1627595445411924e-05,
|
| 620 |
+
"loss": 6.1058,
|
| 621 |
+
"step": 25500
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.51,
|
| 625 |
+
"learning_rate": 4.154551304781792e-05,
|
| 626 |
+
"loss": 6.1346,
|
| 627 |
+
"step": 25750
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.51,
|
| 631 |
+
"learning_rate": 4.146343065022392e-05,
|
| 632 |
+
"loss": 6.0702,
|
| 633 |
+
"step": 26000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.52,
|
| 637 |
+
"learning_rate": 4.138134825262992e-05,
|
| 638 |
+
"loss": 6.0994,
|
| 639 |
+
"step": 26250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.52,
|
| 643 |
+
"learning_rate": 4.129926585503592e-05,
|
| 644 |
+
"loss": 6.0871,
|
| 645 |
+
"step": 26500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.53,
|
| 649 |
+
"learning_rate": 4.121718345744192e-05,
|
| 650 |
+
"loss": 6.0275,
|
| 651 |
+
"step": 26750
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.53,
|
| 655 |
+
"learning_rate": 4.113510105984792e-05,
|
| 656 |
+
"loss": 6.0883,
|
| 657 |
+
"step": 27000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.54,
|
| 661 |
+
"learning_rate": 4.105301866225392e-05,
|
| 662 |
+
"loss": 6.0602,
|
| 663 |
+
"step": 27250
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.54,
|
| 667 |
+
"learning_rate": 4.097093626465992e-05,
|
| 668 |
+
"loss": 5.9898,
|
| 669 |
+
"step": 27500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.55,
|
| 673 |
+
"learning_rate": 4.088885386706592e-05,
|
| 674 |
+
"loss": 6.0722,
|
| 675 |
+
"step": 27750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.55,
|
| 679 |
+
"learning_rate": 4.080677146947192e-05,
|
| 680 |
+
"loss": 5.987,
|
| 681 |
+
"step": 28000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.56,
|
| 685 |
+
"learning_rate": 4.072468907187791e-05,
|
| 686 |
+
"loss": 6.0631,
|
| 687 |
+
"step": 28250
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.56,
|
| 691 |
+
"learning_rate": 4.064260667428392e-05,
|
| 692 |
+
"loss": 5.9497,
|
| 693 |
+
"step": 28500
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.57,
|
| 697 |
+
"learning_rate": 4.056052427668992e-05,
|
| 698 |
+
"loss": 5.9776,
|
| 699 |
+
"step": 28750
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.57,
|
| 703 |
+
"learning_rate": 4.047844187909591e-05,
|
| 704 |
+
"loss": 5.9793,
|
| 705 |
+
"step": 29000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.58,
|
| 709 |
+
"learning_rate": 4.039635948150191e-05,
|
| 710 |
+
"loss": 6.004,
|
| 711 |
+
"step": 29250
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.58,
|
| 715 |
+
"learning_rate": 4.0314277083907916e-05,
|
| 716 |
+
"loss": 5.9236,
|
| 717 |
+
"step": 29500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.59,
|
| 721 |
+
"learning_rate": 4.0232194686313915e-05,
|
| 722 |
+
"loss": 5.9507,
|
| 723 |
+
"step": 29750
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.59,
|
| 727 |
+
"learning_rate": 4.015011228871991e-05,
|
| 728 |
+
"loss": 5.9362,
|
| 729 |
+
"step": 30000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.6,
|
| 733 |
+
"learning_rate": 4.006802989112591e-05,
|
| 734 |
+
"loss": 5.9727,
|
| 735 |
+
"step": 30250
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.6,
|
| 739 |
+
"learning_rate": 3.9985947493531914e-05,
|
| 740 |
+
"loss": 5.8949,
|
| 741 |
+
"step": 30500
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.61,
|
| 745 |
+
"learning_rate": 3.9903865095937906e-05,
|
| 746 |
+
"loss": 5.9043,
|
| 747 |
+
"step": 30750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.61,
|
| 751 |
+
"learning_rate": 3.9821782698343906e-05,
|
| 752 |
+
"loss": 5.8899,
|
| 753 |
+
"step": 31000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.62,
|
| 757 |
+
"learning_rate": 3.9739700300749905e-05,
|
| 758 |
+
"loss": 5.8585,
|
| 759 |
+
"step": 31250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.62,
|
| 763 |
+
"learning_rate": 3.9657617903155905e-05,
|
| 764 |
+
"loss": 5.8793,
|
| 765 |
+
"step": 31500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.63,
|
| 769 |
+
"learning_rate": 3.9575535505561904e-05,
|
| 770 |
+
"loss": 5.8836,
|
| 771 |
+
"step": 31750
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.63,
|
| 775 |
+
"learning_rate": 3.9493453107967904e-05,
|
| 776 |
+
"loss": 5.8597,
|
| 777 |
+
"step": 32000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.64,
|
| 781 |
+
"learning_rate": 3.94113707103739e-05,
|
| 782 |
+
"loss": 5.8795,
|
| 783 |
+
"step": 32250
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.64,
|
| 787 |
+
"learning_rate": 3.93292883127799e-05,
|
| 788 |
+
"loss": 5.8787,
|
| 789 |
+
"step": 32500
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.65,
|
| 793 |
+
"learning_rate": 3.92472059151859e-05,
|
| 794 |
+
"loss": 5.8603,
|
| 795 |
+
"step": 32750
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.65,
|
| 799 |
+
"learning_rate": 3.91651235175919e-05,
|
| 800 |
+
"loss": 5.8186,
|
| 801 |
+
"step": 33000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.66,
|
| 805 |
+
"learning_rate": 3.90830411199979e-05,
|
| 806 |
+
"loss": 5.7699,
|
| 807 |
+
"step": 33250
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.66,
|
| 811 |
+
"learning_rate": 3.90009587224039e-05,
|
| 812 |
+
"loss": 5.7936,
|
| 813 |
+
"step": 33500
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.66,
|
| 817 |
+
"learning_rate": 3.89188763248099e-05,
|
| 818 |
+
"loss": 5.7771,
|
| 819 |
+
"step": 33750
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.67,
|
| 823 |
+
"learning_rate": 3.88367939272159e-05,
|
| 824 |
+
"loss": 5.7897,
|
| 825 |
+
"step": 34000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.67,
|
| 829 |
+
"learning_rate": 3.875471152962189e-05,
|
| 830 |
+
"loss": 5.7541,
|
| 831 |
+
"step": 34250
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.68,
|
| 835 |
+
"learning_rate": 3.86726291320279e-05,
|
| 836 |
+
"loss": 5.7193,
|
| 837 |
+
"step": 34500
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.68,
|
| 841 |
+
"learning_rate": 3.85905467344339e-05,
|
| 842 |
+
"loss": 5.7607,
|
| 843 |
+
"step": 34750
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.69,
|
| 847 |
+
"learning_rate": 3.85084643368399e-05,
|
| 848 |
+
"loss": 5.743,
|
| 849 |
+
"step": 35000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.69,
|
| 853 |
+
"learning_rate": 3.842638193924589e-05,
|
| 854 |
+
"loss": 5.7274,
|
| 855 |
+
"step": 35250
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.7,
|
| 859 |
+
"learning_rate": 3.8344299541651897e-05,
|
| 860 |
+
"loss": 5.7183,
|
| 861 |
+
"step": 35500
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.7,
|
| 865 |
+
"learning_rate": 3.8262217144057896e-05,
|
| 866 |
+
"loss": 5.6701,
|
| 867 |
+
"step": 35750
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.71,
|
| 871 |
+
"learning_rate": 3.818013474646389e-05,
|
| 872 |
+
"loss": 5.7014,
|
| 873 |
+
"step": 36000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.71,
|
| 877 |
+
"learning_rate": 3.809805234886989e-05,
|
| 878 |
+
"loss": 5.684,
|
| 879 |
+
"step": 36250
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.72,
|
| 883 |
+
"learning_rate": 3.8015969951275895e-05,
|
| 884 |
+
"loss": 5.697,
|
| 885 |
+
"step": 36500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.72,
|
| 889 |
+
"learning_rate": 3.793388755368189e-05,
|
| 890 |
+
"loss": 5.6821,
|
| 891 |
+
"step": 36750
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.73,
|
| 895 |
+
"learning_rate": 3.785180515608789e-05,
|
| 896 |
+
"loss": 5.739,
|
| 897 |
+
"step": 37000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.73,
|
| 901 |
+
"learning_rate": 3.7769722758493886e-05,
|
| 902 |
+
"loss": 5.6367,
|
| 903 |
+
"step": 37250
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.74,
|
| 907 |
+
"learning_rate": 3.768764036089989e-05,
|
| 908 |
+
"loss": 5.625,
|
| 909 |
+
"step": 37500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.74,
|
| 913 |
+
"learning_rate": 3.7605557963305885e-05,
|
| 914 |
+
"loss": 5.6101,
|
| 915 |
+
"step": 37750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.75,
|
| 919 |
+
"learning_rate": 3.7523475565711885e-05,
|
| 920 |
+
"loss": 5.6124,
|
| 921 |
+
"step": 38000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.75,
|
| 925 |
+
"learning_rate": 3.7441393168117884e-05,
|
| 926 |
+
"loss": 5.6286,
|
| 927 |
+
"step": 38250
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.76,
|
| 931 |
+
"learning_rate": 3.7359310770523884e-05,
|
| 932 |
+
"loss": 5.6069,
|
| 933 |
+
"step": 38500
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.76,
|
| 937 |
+
"learning_rate": 3.727722837292988e-05,
|
| 938 |
+
"loss": 5.6131,
|
| 939 |
+
"step": 38750
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.77,
|
| 943 |
+
"learning_rate": 3.719514597533588e-05,
|
| 944 |
+
"loss": 5.588,
|
| 945 |
+
"step": 39000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.77,
|
| 949 |
+
"learning_rate": 3.711306357774188e-05,
|
| 950 |
+
"loss": 5.5794,
|
| 951 |
+
"step": 39250
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.78,
|
| 955 |
+
"learning_rate": 3.703098118014788e-05,
|
| 956 |
+
"loss": 5.6147,
|
| 957 |
+
"step": 39500
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.78,
|
| 961 |
+
"learning_rate": 3.694889878255388e-05,
|
| 962 |
+
"loss": 5.5989,
|
| 963 |
+
"step": 39750
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.79,
|
| 967 |
+
"learning_rate": 3.686681638495988e-05,
|
| 968 |
+
"loss": 5.5775,
|
| 969 |
+
"step": 40000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.79,
|
| 973 |
+
"learning_rate": 3.678473398736588e-05,
|
| 974 |
+
"loss": 5.554,
|
| 975 |
+
"step": 40250
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.8,
|
| 979 |
+
"learning_rate": 3.670265158977188e-05,
|
| 980 |
+
"loss": 5.6252,
|
| 981 |
+
"step": 40500
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.8,
|
| 985 |
+
"learning_rate": 3.662056919217788e-05,
|
| 986 |
+
"loss": 5.575,
|
| 987 |
+
"step": 40750
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.81,
|
| 991 |
+
"learning_rate": 3.653848679458388e-05,
|
| 992 |
+
"loss": 5.5285,
|
| 993 |
+
"step": 41000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.81,
|
| 997 |
+
"learning_rate": 3.645640439698987e-05,
|
| 998 |
+
"loss": 5.5481,
|
| 999 |
+
"step": 41250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.82,
|
| 1003 |
+
"learning_rate": 3.637432199939588e-05,
|
| 1004 |
+
"loss": 5.4834,
|
| 1005 |
+
"step": 41500
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.82,
|
| 1009 |
+
"learning_rate": 3.629223960180188e-05,
|
| 1010 |
+
"loss": 5.5461,
|
| 1011 |
+
"step": 41750
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.83,
|
| 1015 |
+
"learning_rate": 3.621015720420787e-05,
|
| 1016 |
+
"loss": 5.5474,
|
| 1017 |
+
"step": 42000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.83,
|
| 1021 |
+
"learning_rate": 3.612807480661387e-05,
|
| 1022 |
+
"loss": 5.53,
|
| 1023 |
+
"step": 42250
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.84,
|
| 1027 |
+
"learning_rate": 3.6045992409019876e-05,
|
| 1028 |
+
"loss": 5.4902,
|
| 1029 |
+
"step": 42500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.84,
|
| 1033 |
+
"learning_rate": 3.5963910011425875e-05,
|
| 1034 |
+
"loss": 5.4589,
|
| 1035 |
+
"step": 42750
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.85,
|
| 1039 |
+
"learning_rate": 3.588182761383187e-05,
|
| 1040 |
+
"loss": 5.4909,
|
| 1041 |
+
"step": 43000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.85,
|
| 1045 |
+
"learning_rate": 3.579974521623787e-05,
|
| 1046 |
+
"loss": 5.4721,
|
| 1047 |
+
"step": 43250
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.86,
|
| 1051 |
+
"learning_rate": 3.5717662818643874e-05,
|
| 1052 |
+
"loss": 5.5191,
|
| 1053 |
+
"step": 43500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.86,
|
| 1057 |
+
"learning_rate": 3.5635580421049866e-05,
|
| 1058 |
+
"loss": 5.4646,
|
| 1059 |
+
"step": 43750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.87,
|
| 1063 |
+
"learning_rate": 3.5553498023455866e-05,
|
| 1064 |
+
"loss": 5.4786,
|
| 1065 |
+
"step": 44000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.87,
|
| 1069 |
+
"learning_rate": 3.5471415625861865e-05,
|
| 1070 |
+
"loss": 5.4943,
|
| 1071 |
+
"step": 44250
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.88,
|
| 1075 |
+
"learning_rate": 3.5389333228267865e-05,
|
| 1076 |
+
"loss": 5.443,
|
| 1077 |
+
"step": 44500
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.88,
|
| 1081 |
+
"learning_rate": 3.5307250830673864e-05,
|
| 1082 |
+
"loss": 5.4313,
|
| 1083 |
+
"step": 44750
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.89,
|
| 1087 |
+
"learning_rate": 3.5225168433079864e-05,
|
| 1088 |
+
"loss": 5.4594,
|
| 1089 |
+
"step": 45000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.89,
|
| 1093 |
+
"learning_rate": 3.514308603548586e-05,
|
| 1094 |
+
"loss": 5.4203,
|
| 1095 |
+
"step": 45250
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.9,
|
| 1099 |
+
"learning_rate": 3.506100363789186e-05,
|
| 1100 |
+
"loss": 5.3763,
|
| 1101 |
+
"step": 45500
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.9,
|
| 1105 |
+
"learning_rate": 3.497892124029786e-05,
|
| 1106 |
+
"loss": 5.445,
|
| 1107 |
+
"step": 45750
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.91,
|
| 1111 |
+
"learning_rate": 3.489683884270386e-05,
|
| 1112 |
+
"loss": 5.4139,
|
| 1113 |
+
"step": 46000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.91,
|
| 1117 |
+
"learning_rate": 3.481475644510986e-05,
|
| 1118 |
+
"loss": 5.3907,
|
| 1119 |
+
"step": 46250
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.92,
|
| 1123 |
+
"learning_rate": 3.473267404751586e-05,
|
| 1124 |
+
"loss": 5.4021,
|
| 1125 |
+
"step": 46500
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.92,
|
| 1129 |
+
"learning_rate": 3.465059164992186e-05,
|
| 1130 |
+
"loss": 5.3955,
|
| 1131 |
+
"step": 46750
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.93,
|
| 1135 |
+
"learning_rate": 3.456850925232786e-05,
|
| 1136 |
+
"loss": 5.3653,
|
| 1137 |
+
"step": 47000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.93,
|
| 1141 |
+
"learning_rate": 3.448642685473385e-05,
|
| 1142 |
+
"loss": 5.3789,
|
| 1143 |
+
"step": 47250
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.94,
|
| 1147 |
+
"learning_rate": 3.440434445713986e-05,
|
| 1148 |
+
"loss": 5.3561,
|
| 1149 |
+
"step": 47500
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.94,
|
| 1153 |
+
"learning_rate": 3.432226205954586e-05,
|
| 1154 |
+
"loss": 5.3199,
|
| 1155 |
+
"step": 47750
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.95,
|
| 1159 |
+
"learning_rate": 3.424017966195186e-05,
|
| 1160 |
+
"loss": 5.3322,
|
| 1161 |
+
"step": 48000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.95,
|
| 1165 |
+
"learning_rate": 3.415809726435785e-05,
|
| 1166 |
+
"loss": 5.3303,
|
| 1167 |
+
"step": 48250
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.96,
|
| 1171 |
+
"learning_rate": 3.407601486676386e-05,
|
| 1172 |
+
"loss": 5.2998,
|
| 1173 |
+
"step": 48500
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.96,
|
| 1177 |
+
"learning_rate": 3.3993932469169856e-05,
|
| 1178 |
+
"loss": 5.3534,
|
| 1179 |
+
"step": 48750
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.97,
|
| 1183 |
+
"learning_rate": 3.391185007157585e-05,
|
| 1184 |
+
"loss": 5.3316,
|
| 1185 |
+
"step": 49000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.97,
|
| 1189 |
+
"learning_rate": 3.382976767398185e-05,
|
| 1190 |
+
"loss": 5.3047,
|
| 1191 |
+
"step": 49250
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.98,
|
| 1195 |
+
"learning_rate": 3.3747685276387855e-05,
|
| 1196 |
+
"loss": 5.2876,
|
| 1197 |
+
"step": 49500
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.98,
|
| 1201 |
+
"learning_rate": 3.366560287879385e-05,
|
| 1202 |
+
"loss": 5.3265,
|
| 1203 |
+
"step": 49750
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.98,
|
| 1207 |
+
"learning_rate": 3.358352048119985e-05,
|
| 1208 |
+
"loss": 5.2812,
|
| 1209 |
+
"step": 50000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.99,
|
| 1213 |
+
"learning_rate": 3.3501438083605846e-05,
|
| 1214 |
+
"loss": 5.2702,
|
| 1215 |
+
"step": 50250
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.99,
|
| 1219 |
+
"learning_rate": 3.341935568601185e-05,
|
| 1220 |
+
"loss": 5.2525,
|
| 1221 |
+
"step": 50500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.0,
|
| 1225 |
+
"learning_rate": 3.3337273288417845e-05,
|
| 1226 |
+
"loss": 5.293,
|
| 1227 |
+
"step": 50750
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.0,
|
| 1231 |
+
"eval_loss": 5.185632228851318,
|
| 1232 |
+
"eval_runtime": 624.5274,
|
| 1233 |
+
"eval_samples_per_second": 289.038,
|
| 1234 |
+
"eval_steps_per_second": 9.032,
|
| 1235 |
+
"step": 50762
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.0,
|
| 1239 |
+
"learning_rate": 3.3255190890823845e-05,
|
| 1240 |
+
"loss": 5.252,
|
| 1241 |
+
"step": 51000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.01,
|
| 1245 |
+
"learning_rate": 3.3173108493229844e-05,
|
| 1246 |
+
"loss": 5.2646,
|
| 1247 |
+
"step": 51250
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.01,
|
| 1251 |
+
"learning_rate": 3.3091026095635844e-05,
|
| 1252 |
+
"loss": 5.2291,
|
| 1253 |
+
"step": 51500
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.02,
|
| 1257 |
+
"learning_rate": 3.300894369804184e-05,
|
| 1258 |
+
"loss": 5.2391,
|
| 1259 |
+
"step": 51750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.02,
|
| 1263 |
+
"learning_rate": 3.292686130044784e-05,
|
| 1264 |
+
"loss": 5.1969,
|
| 1265 |
+
"step": 52000
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 1.03,
|
| 1269 |
+
"learning_rate": 3.284477890285384e-05,
|
| 1270 |
+
"loss": 5.2636,
|
| 1271 |
+
"step": 52250
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.03,
|
| 1275 |
+
"learning_rate": 3.276269650525984e-05,
|
| 1276 |
+
"loss": 5.23,
|
| 1277 |
+
"step": 52500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.04,
|
| 1281 |
+
"learning_rate": 3.268061410766584e-05,
|
| 1282 |
+
"loss": 5.2188,
|
| 1283 |
+
"step": 52750
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.04,
|
| 1287 |
+
"learning_rate": 3.259853171007184e-05,
|
| 1288 |
+
"loss": 5.2196,
|
| 1289 |
+
"step": 53000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.05,
|
| 1293 |
+
"learning_rate": 3.2516449312477834e-05,
|
| 1294 |
+
"loss": 5.1822,
|
| 1295 |
+
"step": 53250
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.05,
|
| 1299 |
+
"learning_rate": 3.243436691488384e-05,
|
| 1300 |
+
"loss": 5.1899,
|
| 1301 |
+
"step": 53500
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.06,
|
| 1305 |
+
"learning_rate": 3.235228451728984e-05,
|
| 1306 |
+
"loss": 5.1678,
|
| 1307 |
+
"step": 53750
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 1.06,
|
| 1311 |
+
"learning_rate": 3.227020211969584e-05,
|
| 1312 |
+
"loss": 5.1901,
|
| 1313 |
+
"step": 54000
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.07,
|
| 1317 |
+
"learning_rate": 3.218811972210183e-05,
|
| 1318 |
+
"loss": 5.2002,
|
| 1319 |
+
"step": 54250
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.07,
|
| 1323 |
+
"learning_rate": 3.210603732450784e-05,
|
| 1324 |
+
"loss": 5.1926,
|
| 1325 |
+
"step": 54500
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.08,
|
| 1329 |
+
"learning_rate": 3.202395492691384e-05,
|
| 1330 |
+
"loss": 5.1494,
|
| 1331 |
+
"step": 54750
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.08,
|
| 1335 |
+
"learning_rate": 3.194187252931983e-05,
|
| 1336 |
+
"loss": 5.1964,
|
| 1337 |
+
"step": 55000
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.09,
|
| 1341 |
+
"learning_rate": 3.185979013172583e-05,
|
| 1342 |
+
"loss": 5.1541,
|
| 1343 |
+
"step": 55250
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.09,
|
| 1347 |
+
"learning_rate": 3.1777707734131836e-05,
|
| 1348 |
+
"loss": 5.1612,
|
| 1349 |
+
"step": 55500
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.1,
|
| 1353 |
+
"learning_rate": 3.1695625336537835e-05,
|
| 1354 |
+
"loss": 5.1887,
|
| 1355 |
+
"step": 55750
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.1,
|
| 1359 |
+
"learning_rate": 3.161354293894383e-05,
|
| 1360 |
+
"loss": 5.16,
|
| 1361 |
+
"step": 56000
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.11,
|
| 1365 |
+
"learning_rate": 3.153146054134983e-05,
|
| 1366 |
+
"loss": 5.1533,
|
| 1367 |
+
"step": 56250
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.11,
|
| 1371 |
+
"learning_rate": 3.1449378143755834e-05,
|
| 1372 |
+
"loss": 5.1851,
|
| 1373 |
+
"step": 56500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.12,
|
| 1377 |
+
"learning_rate": 3.1367295746161826e-05,
|
| 1378 |
+
"loss": 5.1552,
|
| 1379 |
+
"step": 56750
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.12,
|
| 1383 |
+
"learning_rate": 3.1285213348567826e-05,
|
| 1384 |
+
"loss": 5.1378,
|
| 1385 |
+
"step": 57000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.13,
|
| 1389 |
+
"learning_rate": 3.1203130950973825e-05,
|
| 1390 |
+
"loss": 5.118,
|
| 1391 |
+
"step": 57250
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 1.13,
|
| 1395 |
+
"learning_rate": 3.1121048553379825e-05,
|
| 1396 |
+
"loss": 5.1494,
|
| 1397 |
+
"step": 57500
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.14,
|
| 1401 |
+
"learning_rate": 3.1038966155785824e-05,
|
| 1402 |
+
"loss": 5.0843,
|
| 1403 |
+
"step": 57750
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.14,
|
| 1407 |
+
"learning_rate": 3.0956883758191824e-05,
|
| 1408 |
+
"loss": 5.097,
|
| 1409 |
+
"step": 58000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.15,
|
| 1413 |
+
"learning_rate": 3.0874801360597823e-05,
|
| 1414 |
+
"loss": 5.103,
|
| 1415 |
+
"step": 58250
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.15,
|
| 1419 |
+
"learning_rate": 3.079271896300382e-05,
|
| 1420 |
+
"loss": 5.0778,
|
| 1421 |
+
"step": 58500
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 1.16,
|
| 1425 |
+
"learning_rate": 3.071063656540982e-05,
|
| 1426 |
+
"loss": 5.0565,
|
| 1427 |
+
"step": 58750
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.16,
|
| 1431 |
+
"learning_rate": 3.062855416781582e-05,
|
| 1432 |
+
"loss": 5.1443,
|
| 1433 |
+
"step": 59000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 1.17,
|
| 1437 |
+
"learning_rate": 3.054647177022182e-05,
|
| 1438 |
+
"loss": 5.0715,
|
| 1439 |
+
"step": 59250
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.17,
|
| 1443 |
+
"learning_rate": 3.046438937262782e-05,
|
| 1444 |
+
"loss": 5.0871,
|
| 1445 |
+
"step": 59500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.18,
|
| 1449 |
+
"learning_rate": 3.038230697503382e-05,
|
| 1450 |
+
"loss": 5.0992,
|
| 1451 |
+
"step": 59750
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.18,
|
| 1455 |
+
"learning_rate": 3.0300224577439816e-05,
|
| 1456 |
+
"loss": 5.0874,
|
| 1457 |
+
"step": 60000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.19,
|
| 1461 |
+
"learning_rate": 3.0218142179845816e-05,
|
| 1462 |
+
"loss": 5.1127,
|
| 1463 |
+
"step": 60250
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.19,
|
| 1467 |
+
"learning_rate": 3.013605978225182e-05,
|
| 1468 |
+
"loss": 5.0684,
|
| 1469 |
+
"step": 60500
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 1.2,
|
| 1473 |
+
"learning_rate": 3.0053977384657815e-05,
|
| 1474 |
+
"loss": 5.0856,
|
| 1475 |
+
"step": 60750
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 1.2,
|
| 1479 |
+
"learning_rate": 2.9971894987063814e-05,
|
| 1480 |
+
"loss": 5.062,
|
| 1481 |
+
"step": 61000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.21,
|
| 1485 |
+
"learning_rate": 2.988981258946981e-05,
|
| 1486 |
+
"loss": 5.0753,
|
| 1487 |
+
"step": 61250
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.21,
|
| 1491 |
+
"learning_rate": 2.9807730191875817e-05,
|
| 1492 |
+
"loss": 5.055,
|
| 1493 |
+
"step": 61500
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.22,
|
| 1497 |
+
"learning_rate": 2.9725647794281813e-05,
|
| 1498 |
+
"loss": 5.0444,
|
| 1499 |
+
"step": 61750
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.22,
|
| 1503 |
+
"learning_rate": 2.9643565396687812e-05,
|
| 1504 |
+
"loss": 5.0642,
|
| 1505 |
+
"step": 62000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.23,
|
| 1509 |
+
"learning_rate": 2.956148299909381e-05,
|
| 1510 |
+
"loss": 5.0566,
|
| 1511 |
+
"step": 62250
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.23,
|
| 1515 |
+
"learning_rate": 2.947940060149981e-05,
|
| 1516 |
+
"loss": 5.0445,
|
| 1517 |
+
"step": 62500
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 1.24,
|
| 1521 |
+
"learning_rate": 2.939731820390581e-05,
|
| 1522 |
+
"loss": 5.0221,
|
| 1523 |
+
"step": 62750
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.24,
|
| 1527 |
+
"learning_rate": 2.9315235806311807e-05,
|
| 1528 |
+
"loss": 5.0624,
|
| 1529 |
+
"step": 63000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.25,
|
| 1533 |
+
"learning_rate": 2.9233153408717807e-05,
|
| 1534 |
+
"loss": 5.0271,
|
| 1535 |
+
"step": 63250
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.25,
|
| 1539 |
+
"learning_rate": 2.915107101112381e-05,
|
| 1540 |
+
"loss": 5.0478,
|
| 1541 |
+
"step": 63500
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.26,
|
| 1545 |
+
"learning_rate": 2.906898861352981e-05,
|
| 1546 |
+
"loss": 5.0316,
|
| 1547 |
+
"step": 63750
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 1.26,
|
| 1551 |
+
"learning_rate": 2.8986906215935805e-05,
|
| 1552 |
+
"loss": 4.9997,
|
| 1553 |
+
"step": 64000
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 1.27,
|
| 1557 |
+
"learning_rate": 2.8904823818341804e-05,
|
| 1558 |
+
"loss": 4.9997,
|
| 1559 |
+
"step": 64250
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 1.27,
|
| 1563 |
+
"learning_rate": 2.8822741420747807e-05,
|
| 1564 |
+
"loss": 5.0058,
|
| 1565 |
+
"step": 64500
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.28,
|
| 1569 |
+
"learning_rate": 2.8740659023153803e-05,
|
| 1570 |
+
"loss": 4.9975,
|
| 1571 |
+
"step": 64750
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.28,
|
| 1575 |
+
"learning_rate": 2.8658576625559803e-05,
|
| 1576 |
+
"loss": 4.9933,
|
| 1577 |
+
"step": 65000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.29,
|
| 1581 |
+
"learning_rate": 2.85764942279658e-05,
|
| 1582 |
+
"loss": 4.9868,
|
| 1583 |
+
"step": 65250
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.29,
|
| 1587 |
+
"learning_rate": 2.8494411830371802e-05,
|
| 1588 |
+
"loss": 4.981,
|
| 1589 |
+
"step": 65500
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 1.3,
|
| 1593 |
+
"learning_rate": 2.84123294327778e-05,
|
| 1594 |
+
"loss": 5.0185,
|
| 1595 |
+
"step": 65750
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 1.3,
|
| 1599 |
+
"learning_rate": 2.8330247035183798e-05,
|
| 1600 |
+
"loss": 4.9715,
|
| 1601 |
+
"step": 66000
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 1.31,
|
| 1605 |
+
"learning_rate": 2.8248164637589797e-05,
|
| 1606 |
+
"loss": 5.0356,
|
| 1607 |
+
"step": 66250
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.31,
|
| 1611 |
+
"learning_rate": 2.81660822399958e-05,
|
| 1612 |
+
"loss": 4.9427,
|
| 1613 |
+
"step": 66500
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.31,
|
| 1617 |
+
"learning_rate": 2.80839998424018e-05,
|
| 1618 |
+
"loss": 4.8855,
|
| 1619 |
+
"step": 66750
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.32,
|
| 1623 |
+
"learning_rate": 2.8001917444807796e-05,
|
| 1624 |
+
"loss": 4.9676,
|
| 1625 |
+
"step": 67000
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.32,
|
| 1629 |
+
"learning_rate": 2.7919835047213795e-05,
|
| 1630 |
+
"loss": 4.9374,
|
| 1631 |
+
"step": 67250
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 1.33,
|
| 1635 |
+
"learning_rate": 2.7837752649619798e-05,
|
| 1636 |
+
"loss": 4.9648,
|
| 1637 |
+
"step": 67500
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 1.33,
|
| 1641 |
+
"learning_rate": 2.7755670252025794e-05,
|
| 1642 |
+
"loss": 4.9769,
|
| 1643 |
+
"step": 67750
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.34,
|
| 1647 |
+
"learning_rate": 2.7673587854431793e-05,
|
| 1648 |
+
"loss": 4.8962,
|
| 1649 |
+
"step": 68000
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.34,
|
| 1653 |
+
"learning_rate": 2.759150545683779e-05,
|
| 1654 |
+
"loss": 4.9559,
|
| 1655 |
+
"step": 68250
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.35,
|
| 1659 |
+
"learning_rate": 2.7509423059243792e-05,
|
| 1660 |
+
"loss": 4.929,
|
| 1661 |
+
"step": 68500
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.35,
|
| 1665 |
+
"learning_rate": 2.7427340661649792e-05,
|
| 1666 |
+
"loss": 4.946,
|
| 1667 |
+
"step": 68750
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.36,
|
| 1671 |
+
"learning_rate": 2.7345258264055788e-05,
|
| 1672 |
+
"loss": 4.9562,
|
| 1673 |
+
"step": 69000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.36,
|
| 1677 |
+
"learning_rate": 2.7263175866461788e-05,
|
| 1678 |
+
"loss": 4.9309,
|
| 1679 |
+
"step": 69250
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 1.37,
|
| 1683 |
+
"learning_rate": 2.718109346886779e-05,
|
| 1684 |
+
"loss": 4.9074,
|
| 1685 |
+
"step": 69500
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.37,
|
| 1689 |
+
"learning_rate": 2.709901107127379e-05,
|
| 1690 |
+
"loss": 4.8918,
|
| 1691 |
+
"step": 69750
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.38,
|
| 1695 |
+
"learning_rate": 2.7016928673679786e-05,
|
| 1696 |
+
"loss": 4.9262,
|
| 1697 |
+
"step": 70000
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.38,
|
| 1701 |
+
"learning_rate": 2.6934846276085786e-05,
|
| 1702 |
+
"loss": 4.8864,
|
| 1703 |
+
"step": 70250
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.39,
|
| 1707 |
+
"learning_rate": 2.685276387849179e-05,
|
| 1708 |
+
"loss": 4.9013,
|
| 1709 |
+
"step": 70500
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 1.39,
|
| 1713 |
+
"learning_rate": 2.6770681480897785e-05,
|
| 1714 |
+
"loss": 4.8744,
|
| 1715 |
+
"step": 70750
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.4,
|
| 1719 |
+
"learning_rate": 2.6688599083303784e-05,
|
| 1720 |
+
"loss": 4.881,
|
| 1721 |
+
"step": 71000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.4,
|
| 1725 |
+
"learning_rate": 2.6606516685709787e-05,
|
| 1726 |
+
"loss": 4.911,
|
| 1727 |
+
"step": 71250
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 1.41,
|
| 1731 |
+
"learning_rate": 2.6524434288115786e-05,
|
| 1732 |
+
"loss": 4.8839,
|
| 1733 |
+
"step": 71500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.41,
|
| 1737 |
+
"learning_rate": 2.6442351890521783e-05,
|
| 1738 |
+
"loss": 4.8996,
|
| 1739 |
+
"step": 71750
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.42,
|
| 1743 |
+
"learning_rate": 2.6360269492927782e-05,
|
| 1744 |
+
"loss": 4.9019,
|
| 1745 |
+
"step": 72000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.42,
|
| 1749 |
+
"learning_rate": 2.6278187095333785e-05,
|
| 1750 |
+
"loss": 4.8942,
|
| 1751 |
+
"step": 72250
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 1.43,
|
| 1755 |
+
"learning_rate": 2.619610469773978e-05,
|
| 1756 |
+
"loss": 4.8242,
|
| 1757 |
+
"step": 72500
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.43,
|
| 1761 |
+
"learning_rate": 2.611402230014578e-05,
|
| 1762 |
+
"loss": 4.8776,
|
| 1763 |
+
"step": 72750
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 1.44,
|
| 1767 |
+
"learning_rate": 2.6031939902551777e-05,
|
| 1768 |
+
"loss": 4.8732,
|
| 1769 |
+
"step": 73000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.44,
|
| 1773 |
+
"learning_rate": 2.594985750495778e-05,
|
| 1774 |
+
"loss": 4.8902,
|
| 1775 |
+
"step": 73250
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 1.45,
|
| 1779 |
+
"learning_rate": 2.586777510736378e-05,
|
| 1780 |
+
"loss": 4.8638,
|
| 1781 |
+
"step": 73500
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.45,
|
| 1785 |
+
"learning_rate": 2.5785692709769775e-05,
|
| 1786 |
+
"loss": 4.8418,
|
| 1787 |
+
"step": 73750
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.46,
|
| 1791 |
+
"learning_rate": 2.5703610312175775e-05,
|
| 1792 |
+
"loss": 4.8541,
|
| 1793 |
+
"step": 74000
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.46,
|
| 1797 |
+
"learning_rate": 2.5621527914581777e-05,
|
| 1798 |
+
"loss": 4.8397,
|
| 1799 |
+
"step": 74250
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 1.47,
|
| 1803 |
+
"learning_rate": 2.5539445516987777e-05,
|
| 1804 |
+
"loss": 4.8609,
|
| 1805 |
+
"step": 74500
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 1.47,
|
| 1809 |
+
"learning_rate": 2.5457363119393773e-05,
|
| 1810 |
+
"loss": 4.8698,
|
| 1811 |
+
"step": 74750
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.48,
|
| 1815 |
+
"learning_rate": 2.5375280721799773e-05,
|
| 1816 |
+
"loss": 4.88,
|
| 1817 |
+
"step": 75000
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.48,
|
| 1821 |
+
"learning_rate": 2.5293198324205775e-05,
|
| 1822 |
+
"loss": 4.8273,
|
| 1823 |
+
"step": 75250
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.49,
|
| 1827 |
+
"learning_rate": 2.521111592661177e-05,
|
| 1828 |
+
"loss": 4.8285,
|
| 1829 |
+
"step": 75500
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.49,
|
| 1833 |
+
"learning_rate": 2.512903352901777e-05,
|
| 1834 |
+
"loss": 4.853,
|
| 1835 |
+
"step": 75750
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.5,
|
| 1839 |
+
"learning_rate": 2.5046951131423767e-05,
|
| 1840 |
+
"loss": 4.8384,
|
| 1841 |
+
"step": 76000
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 1.5,
|
| 1845 |
+
"learning_rate": 2.496486873382977e-05,
|
| 1846 |
+
"loss": 4.7944,
|
| 1847 |
+
"step": 76250
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 1.51,
|
| 1851 |
+
"learning_rate": 2.488278633623577e-05,
|
| 1852 |
+
"loss": 4.8423,
|
| 1853 |
+
"step": 76500
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 1.51,
|
| 1857 |
+
"learning_rate": 2.4800703938641766e-05,
|
| 1858 |
+
"loss": 4.797,
|
| 1859 |
+
"step": 76750
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 1.52,
|
| 1863 |
+
"learning_rate": 2.471862154104777e-05,
|
| 1864 |
+
"loss": 4.7585,
|
| 1865 |
+
"step": 77000
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.52,
|
| 1869 |
+
"learning_rate": 2.4636539143453765e-05,
|
| 1870 |
+
"loss": 4.8479,
|
| 1871 |
+
"step": 77250
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.53,
|
| 1875 |
+
"learning_rate": 2.4554456745859767e-05,
|
| 1876 |
+
"loss": 4.7687,
|
| 1877 |
+
"step": 77500
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.53,
|
| 1881 |
+
"learning_rate": 2.4472374348265764e-05,
|
| 1882 |
+
"loss": 4.793,
|
| 1883 |
+
"step": 77750
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 1.54,
|
| 1887 |
+
"learning_rate": 2.4390291950671763e-05,
|
| 1888 |
+
"loss": 4.8033,
|
| 1889 |
+
"step": 78000
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 1.54,
|
| 1893 |
+
"learning_rate": 2.4308209553077763e-05,
|
| 1894 |
+
"loss": 4.8058,
|
| 1895 |
+
"step": 78250
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 1.55,
|
| 1899 |
+
"learning_rate": 2.4226127155483762e-05,
|
| 1900 |
+
"loss": 4.8193,
|
| 1901 |
+
"step": 78500
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.55,
|
| 1905 |
+
"learning_rate": 2.414404475788976e-05,
|
| 1906 |
+
"loss": 4.8197,
|
| 1907 |
+
"step": 78750
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.56,
|
| 1911 |
+
"learning_rate": 2.406196236029576e-05,
|
| 1912 |
+
"loss": 4.817,
|
| 1913 |
+
"step": 79000
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.56,
|
| 1917 |
+
"learning_rate": 2.397987996270176e-05,
|
| 1918 |
+
"loss": 4.7666,
|
| 1919 |
+
"step": 79250
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.57,
|
| 1923 |
+
"learning_rate": 2.389779756510776e-05,
|
| 1924 |
+
"loss": 4.779,
|
| 1925 |
+
"step": 79500
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 1.57,
|
| 1929 |
+
"learning_rate": 2.381571516751376e-05,
|
| 1930 |
+
"loss": 4.7867,
|
| 1931 |
+
"step": 79750
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 1.58,
|
| 1935 |
+
"learning_rate": 2.373363276991976e-05,
|
| 1936 |
+
"loss": 4.711,
|
| 1937 |
+
"step": 80000
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 1.58,
|
| 1941 |
+
"learning_rate": 2.3651550372325755e-05,
|
| 1942 |
+
"loss": 4.764,
|
| 1943 |
+
"step": 80250
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 1.59,
|
| 1947 |
+
"learning_rate": 2.3569467974731758e-05,
|
| 1948 |
+
"loss": 4.7442,
|
| 1949 |
+
"step": 80500
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.59,
|
| 1953 |
+
"learning_rate": 2.3487385577137754e-05,
|
| 1954 |
+
"loss": 4.7251,
|
| 1955 |
+
"step": 80750
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.6,
|
| 1959 |
+
"learning_rate": 2.3405303179543757e-05,
|
| 1960 |
+
"loss": 4.7445,
|
| 1961 |
+
"step": 81000
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.6,
|
| 1965 |
+
"learning_rate": 2.3323220781949753e-05,
|
| 1966 |
+
"loss": 4.7737,
|
| 1967 |
+
"step": 81250
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.61,
|
| 1971 |
+
"learning_rate": 2.3241138384355753e-05,
|
| 1972 |
+
"loss": 4.7479,
|
| 1973 |
+
"step": 81500
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 1.61,
|
| 1977 |
+
"learning_rate": 2.3159055986761752e-05,
|
| 1978 |
+
"loss": 4.7482,
|
| 1979 |
+
"step": 81750
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.62,
|
| 1983 |
+
"learning_rate": 2.307697358916775e-05,
|
| 1984 |
+
"loss": 4.7181,
|
| 1985 |
+
"step": 82000
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 1.62,
|
| 1989 |
+
"learning_rate": 2.299489119157375e-05,
|
| 1990 |
+
"loss": 4.7784,
|
| 1991 |
+
"step": 82250
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.63,
|
| 1995 |
+
"learning_rate": 2.291280879397975e-05,
|
| 1996 |
+
"loss": 4.7506,
|
| 1997 |
+
"step": 82500
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.63,
|
| 2001 |
+
"learning_rate": 2.283072639638575e-05,
|
| 2002 |
+
"loss": 4.7269,
|
| 2003 |
+
"step": 82750
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.64,
|
| 2007 |
+
"learning_rate": 2.274864399879175e-05,
|
| 2008 |
+
"loss": 4.7102,
|
| 2009 |
+
"step": 83000
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 1.64,
|
| 2013 |
+
"learning_rate": 2.2666561601197746e-05,
|
| 2014 |
+
"loss": 4.7706,
|
| 2015 |
+
"step": 83250
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 1.64,
|
| 2019 |
+
"learning_rate": 2.258447920360375e-05,
|
| 2020 |
+
"loss": 4.7343,
|
| 2021 |
+
"step": 83500
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 1.65,
|
| 2025 |
+
"learning_rate": 2.2502396806009745e-05,
|
| 2026 |
+
"loss": 4.6911,
|
| 2027 |
+
"step": 83750
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 1.65,
|
| 2031 |
+
"learning_rate": 2.2420314408415748e-05,
|
| 2032 |
+
"loss": 4.7585,
|
| 2033 |
+
"step": 84000
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.66,
|
| 2037 |
+
"learning_rate": 2.2338232010821744e-05,
|
| 2038 |
+
"loss": 4.6949,
|
| 2039 |
+
"step": 84250
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.66,
|
| 2043 |
+
"learning_rate": 2.2256149613227743e-05,
|
| 2044 |
+
"loss": 4.7423,
|
| 2045 |
+
"step": 84500
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.67,
|
| 2049 |
+
"learning_rate": 2.2174067215633743e-05,
|
| 2050 |
+
"loss": 4.7317,
|
| 2051 |
+
"step": 84750
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.67,
|
| 2055 |
+
"learning_rate": 2.2091984818039742e-05,
|
| 2056 |
+
"loss": 4.7393,
|
| 2057 |
+
"step": 85000
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 1.68,
|
| 2061 |
+
"learning_rate": 2.200990242044574e-05,
|
| 2062 |
+
"loss": 4.7046,
|
| 2063 |
+
"step": 85250
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 1.68,
|
| 2067 |
+
"learning_rate": 2.192782002285174e-05,
|
| 2068 |
+
"loss": 4.77,
|
| 2069 |
+
"step": 85500
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 1.69,
|
| 2073 |
+
"learning_rate": 2.184573762525774e-05,
|
| 2074 |
+
"loss": 4.7457,
|
| 2075 |
+
"step": 85750
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.69,
|
| 2079 |
+
"learning_rate": 2.176365522766374e-05,
|
| 2080 |
+
"loss": 4.6749,
|
| 2081 |
+
"step": 86000
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.7,
|
| 2085 |
+
"learning_rate": 2.168157283006974e-05,
|
| 2086 |
+
"loss": 4.6972,
|
| 2087 |
+
"step": 86250
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.7,
|
| 2091 |
+
"learning_rate": 2.159949043247574e-05,
|
| 2092 |
+
"loss": 4.6846,
|
| 2093 |
+
"step": 86500
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 1.71,
|
| 2097 |
+
"learning_rate": 2.1517408034881735e-05,
|
| 2098 |
+
"loss": 4.7132,
|
| 2099 |
+
"step": 86750
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 1.71,
|
| 2103 |
+
"learning_rate": 2.1435325637287738e-05,
|
| 2104 |
+
"loss": 4.6606,
|
| 2105 |
+
"step": 87000
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 1.72,
|
| 2109 |
+
"learning_rate": 2.1353243239693734e-05,
|
| 2110 |
+
"loss": 4.6989,
|
| 2111 |
+
"step": 87250
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 1.72,
|
| 2115 |
+
"learning_rate": 2.1271160842099737e-05,
|
| 2116 |
+
"loss": 4.7223,
|
| 2117 |
+
"step": 87500
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.73,
|
| 2121 |
+
"learning_rate": 2.1189078444505733e-05,
|
| 2122 |
+
"loss": 4.6806,
|
| 2123 |
+
"step": 87750
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.73,
|
| 2127 |
+
"learning_rate": 2.1106996046911733e-05,
|
| 2128 |
+
"loss": 4.6947,
|
| 2129 |
+
"step": 88000
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 1.74,
|
| 2133 |
+
"learning_rate": 2.1024913649317732e-05,
|
| 2134 |
+
"loss": 4.712,
|
| 2135 |
+
"step": 88250
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 1.74,
|
| 2139 |
+
"learning_rate": 2.094283125172373e-05,
|
| 2140 |
+
"loss": 4.7026,
|
| 2141 |
+
"step": 88500
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 1.75,
|
| 2145 |
+
"learning_rate": 2.086074885412973e-05,
|
| 2146 |
+
"loss": 4.714,
|
| 2147 |
+
"step": 88750
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 1.75,
|
| 2151 |
+
"learning_rate": 2.077866645653573e-05,
|
| 2152 |
+
"loss": 4.6463,
|
| 2153 |
+
"step": 89000
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 1.76,
|
| 2157 |
+
"learning_rate": 2.069658405894173e-05,
|
| 2158 |
+
"loss": 4.6939,
|
| 2159 |
+
"step": 89250
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.76,
|
| 2163 |
+
"learning_rate": 2.061450166134773e-05,
|
| 2164 |
+
"loss": 4.6927,
|
| 2165 |
+
"step": 89500
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.77,
|
| 2169 |
+
"learning_rate": 2.0532419263753726e-05,
|
| 2170 |
+
"loss": 4.6733,
|
| 2171 |
+
"step": 89750
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 1.77,
|
| 2175 |
+
"learning_rate": 2.045033686615973e-05,
|
| 2176 |
+
"loss": 4.6651,
|
| 2177 |
+
"step": 90000
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 1.78,
|
| 2181 |
+
"learning_rate": 2.0368254468565725e-05,
|
| 2182 |
+
"loss": 4.6826,
|
| 2183 |
+
"step": 90250
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 1.78,
|
| 2187 |
+
"learning_rate": 2.0286172070971728e-05,
|
| 2188 |
+
"loss": 4.6593,
|
| 2189 |
+
"step": 90500
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 1.79,
|
| 2193 |
+
"learning_rate": 2.0204089673377724e-05,
|
| 2194 |
+
"loss": 4.6748,
|
| 2195 |
+
"step": 90750
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 1.79,
|
| 2199 |
+
"learning_rate": 2.0122007275783723e-05,
|
| 2200 |
+
"loss": 4.6453,
|
| 2201 |
+
"step": 91000
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.8,
|
| 2205 |
+
"learning_rate": 2.0039924878189723e-05,
|
| 2206 |
+
"loss": 4.6764,
|
| 2207 |
+
"step": 91250
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.8,
|
| 2211 |
+
"learning_rate": 1.9957842480595722e-05,
|
| 2212 |
+
"loss": 4.6282,
|
| 2213 |
+
"step": 91500
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 1.81,
|
| 2217 |
+
"learning_rate": 1.987576008300172e-05,
|
| 2218 |
+
"loss": 4.6437,
|
| 2219 |
+
"step": 91750
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 1.81,
|
| 2223 |
+
"learning_rate": 1.979367768540772e-05,
|
| 2224 |
+
"loss": 4.6456,
|
| 2225 |
+
"step": 92000
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 1.82,
|
| 2229 |
+
"learning_rate": 1.971159528781372e-05,
|
| 2230 |
+
"loss": 4.6155,
|
| 2231 |
+
"step": 92250
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 1.82,
|
| 2235 |
+
"learning_rate": 1.962951289021972e-05,
|
| 2236 |
+
"loss": 4.609,
|
| 2237 |
+
"step": 92500
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.83,
|
| 2241 |
+
"learning_rate": 1.9547430492625716e-05,
|
| 2242 |
+
"loss": 4.6056,
|
| 2243 |
+
"step": 92750
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.83,
|
| 2247 |
+
"learning_rate": 1.946534809503172e-05,
|
| 2248 |
+
"loss": 4.6138,
|
| 2249 |
+
"step": 93000
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.84,
|
| 2253 |
+
"learning_rate": 1.9383265697437715e-05,
|
| 2254 |
+
"loss": 4.6259,
|
| 2255 |
+
"step": 93250
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 1.84,
|
| 2259 |
+
"learning_rate": 1.9301183299843718e-05,
|
| 2260 |
+
"loss": 4.651,
|
| 2261 |
+
"step": 93500
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 1.85,
|
| 2265 |
+
"learning_rate": 1.9219100902249714e-05,
|
| 2266 |
+
"loss": 4.6287,
|
| 2267 |
+
"step": 93750
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 1.85,
|
| 2271 |
+
"learning_rate": 1.9137018504655717e-05,
|
| 2272 |
+
"loss": 4.6163,
|
| 2273 |
+
"step": 94000
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 1.86,
|
| 2277 |
+
"learning_rate": 1.9054936107061713e-05,
|
| 2278 |
+
"loss": 4.5989,
|
| 2279 |
+
"step": 94250
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 1.86,
|
| 2283 |
+
"learning_rate": 1.8972853709467713e-05,
|
| 2284 |
+
"loss": 4.6224,
|
| 2285 |
+
"step": 94500
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.87,
|
| 2289 |
+
"learning_rate": 1.8890771311873712e-05,
|
| 2290 |
+
"loss": 4.5913,
|
| 2291 |
+
"step": 94750
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.87,
|
| 2295 |
+
"learning_rate": 1.8808688914279712e-05,
|
| 2296 |
+
"loss": 4.6267,
|
| 2297 |
+
"step": 95000
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 1.88,
|
| 2301 |
+
"learning_rate": 1.872660651668571e-05,
|
| 2302 |
+
"loss": 4.5906,
|
| 2303 |
+
"step": 95250
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 1.88,
|
| 2307 |
+
"learning_rate": 1.864452411909171e-05,
|
| 2308 |
+
"loss": 4.6433,
|
| 2309 |
+
"step": 95500
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 1.89,
|
| 2313 |
+
"learning_rate": 1.856244172149771e-05,
|
| 2314 |
+
"loss": 4.6444,
|
| 2315 |
+
"step": 95750
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 1.89,
|
| 2319 |
+
"learning_rate": 1.848035932390371e-05,
|
| 2320 |
+
"loss": 4.6358,
|
| 2321 |
+
"step": 96000
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 1.9,
|
| 2325 |
+
"learning_rate": 1.8398276926309706e-05,
|
| 2326 |
+
"loss": 4.577,
|
| 2327 |
+
"step": 96250
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.9,
|
| 2331 |
+
"learning_rate": 1.831619452871571e-05,
|
| 2332 |
+
"loss": 4.6281,
|
| 2333 |
+
"step": 96500
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.91,
|
| 2337 |
+
"learning_rate": 1.8234112131121705e-05,
|
| 2338 |
+
"loss": 4.613,
|
| 2339 |
+
"step": 96750
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 1.91,
|
| 2343 |
+
"learning_rate": 1.8152029733527708e-05,
|
| 2344 |
+
"loss": 4.6085,
|
| 2345 |
+
"step": 97000
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 1.92,
|
| 2349 |
+
"learning_rate": 1.8069947335933704e-05,
|
| 2350 |
+
"loss": 4.6347,
|
| 2351 |
+
"step": 97250
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 1.92,
|
| 2355 |
+
"learning_rate": 1.7987864938339703e-05,
|
| 2356 |
+
"loss": 4.6094,
|
| 2357 |
+
"step": 97500
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 1.93,
|
| 2361 |
+
"learning_rate": 1.7905782540745703e-05,
|
| 2362 |
+
"loss": 4.6255,
|
| 2363 |
+
"step": 97750
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 1.93,
|
| 2367 |
+
"learning_rate": 1.7823700143151702e-05,
|
| 2368 |
+
"loss": 4.5426,
|
| 2369 |
+
"step": 98000
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.94,
|
| 2373 |
+
"learning_rate": 1.7741617745557702e-05,
|
| 2374 |
+
"loss": 4.594,
|
| 2375 |
+
"step": 98250
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.94,
|
| 2379 |
+
"learning_rate": 1.76595353479637e-05,
|
| 2380 |
+
"loss": 4.5371,
|
| 2381 |
+
"step": 98500
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 1.95,
|
| 2385 |
+
"learning_rate": 1.75774529503697e-05,
|
| 2386 |
+
"loss": 4.6085,
|
| 2387 |
+
"step": 98750
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 1.95,
|
| 2391 |
+
"learning_rate": 1.74953705527757e-05,
|
| 2392 |
+
"loss": 4.6097,
|
| 2393 |
+
"step": 99000
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 1.96,
|
| 2397 |
+
"learning_rate": 1.7413288155181696e-05,
|
| 2398 |
+
"loss": 4.5315,
|
| 2399 |
+
"step": 99250
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 1.96,
|
| 2403 |
+
"learning_rate": 1.73312057575877e-05,
|
| 2404 |
+
"loss": 4.5781,
|
| 2405 |
+
"step": 99500
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 1.97,
|
| 2409 |
+
"learning_rate": 1.7249123359993695e-05,
|
| 2410 |
+
"loss": 4.5609,
|
| 2411 |
+
"step": 99750
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.97,
|
| 2415 |
+
"learning_rate": 1.7167040962399698e-05,
|
| 2416 |
+
"loss": 4.5971,
|
| 2417 |
+
"step": 100000
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.97,
|
| 2421 |
+
"learning_rate": 1.7084958564805694e-05,
|
| 2422 |
+
"loss": 4.5534,
|
| 2423 |
+
"step": 100250
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 1.98,
|
| 2427 |
+
"learning_rate": 1.7002876167211694e-05,
|
| 2428 |
+
"loss": 4.5275,
|
| 2429 |
+
"step": 100500
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 1.98,
|
| 2433 |
+
"learning_rate": 1.6920793769617693e-05,
|
| 2434 |
+
"loss": 4.5443,
|
| 2435 |
+
"step": 100750
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 1.99,
|
| 2439 |
+
"learning_rate": 1.6838711372023693e-05,
|
| 2440 |
+
"loss": 4.5559,
|
| 2441 |
+
"step": 101000
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 1.99,
|
| 2445 |
+
"learning_rate": 1.6756628974429692e-05,
|
| 2446 |
+
"loss": 4.5289,
|
| 2447 |
+
"step": 101250
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 2.0,
|
| 2451 |
+
"learning_rate": 1.6674546576835692e-05,
|
| 2452 |
+
"loss": 4.574,
|
| 2453 |
+
"step": 101500
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.0,
|
| 2457 |
+
"eval_loss": 4.450372695922852,
|
| 2458 |
+
"eval_runtime": 619.9479,
|
| 2459 |
+
"eval_samples_per_second": 291.173,
|
| 2460 |
+
"eval_steps_per_second": 9.099,
|
| 2461 |
+
"step": 101524
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 2.0,
|
| 2465 |
+
"learning_rate": 1.659246417924169e-05,
|
| 2466 |
+
"loss": 4.4787,
|
| 2467 |
+
"step": 101750
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.01,
|
| 2471 |
+
"learning_rate": 1.651038178164769e-05,
|
| 2472 |
+
"loss": 4.5425,
|
| 2473 |
+
"step": 102000
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.01,
|
| 2477 |
+
"learning_rate": 1.642829938405369e-05,
|
| 2478 |
+
"loss": 4.5304,
|
| 2479 |
+
"step": 102250
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 2.02,
|
| 2483 |
+
"learning_rate": 1.634621698645969e-05,
|
| 2484 |
+
"loss": 4.5141,
|
| 2485 |
+
"step": 102500
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 2.02,
|
| 2489 |
+
"learning_rate": 1.6264134588865686e-05,
|
| 2490 |
+
"loss": 4.5189,
|
| 2491 |
+
"step": 102750
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 2.03,
|
| 2495 |
+
"learning_rate": 1.618205219127169e-05,
|
| 2496 |
+
"loss": 4.5433,
|
| 2497 |
+
"step": 103000
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 2.03,
|
| 2501 |
+
"learning_rate": 1.6099969793677685e-05,
|
| 2502 |
+
"loss": 4.561,
|
| 2503 |
+
"step": 103250
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 2.04,
|
| 2507 |
+
"learning_rate": 1.6017887396083688e-05,
|
| 2508 |
+
"loss": 4.5514,
|
| 2509 |
+
"step": 103500
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 2.04,
|
| 2513 |
+
"learning_rate": 1.5935804998489684e-05,
|
| 2514 |
+
"loss": 4.5083,
|
| 2515 |
+
"step": 103750
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 2.05,
|
| 2519 |
+
"learning_rate": 1.5853722600895683e-05,
|
| 2520 |
+
"loss": 4.524,
|
| 2521 |
+
"step": 104000
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 2.05,
|
| 2525 |
+
"learning_rate": 1.5771640203301683e-05,
|
| 2526 |
+
"loss": 4.5076,
|
| 2527 |
+
"step": 104250
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"epoch": 2.06,
|
| 2531 |
+
"learning_rate": 1.5689557805707682e-05,
|
| 2532 |
+
"loss": 4.5146,
|
| 2533 |
+
"step": 104500
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"epoch": 2.06,
|
| 2537 |
+
"learning_rate": 1.5607475408113682e-05,
|
| 2538 |
+
"loss": 4.4952,
|
| 2539 |
+
"step": 104750
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 2.07,
|
| 2543 |
+
"learning_rate": 1.552539301051968e-05,
|
| 2544 |
+
"loss": 4.513,
|
| 2545 |
+
"step": 105000
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 2.07,
|
| 2549 |
+
"learning_rate": 1.544331061292568e-05,
|
| 2550 |
+
"loss": 4.5001,
|
| 2551 |
+
"step": 105250
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.08,
|
| 2555 |
+
"learning_rate": 1.536122821533168e-05,
|
| 2556 |
+
"loss": 4.5537,
|
| 2557 |
+
"step": 105500
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.08,
|
| 2561 |
+
"learning_rate": 1.5279145817737676e-05,
|
| 2562 |
+
"loss": 4.5184,
|
| 2563 |
+
"step": 105750
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 2.09,
|
| 2567 |
+
"learning_rate": 1.519706342014368e-05,
|
| 2568 |
+
"loss": 4.4982,
|
| 2569 |
+
"step": 106000
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 2.09,
|
| 2573 |
+
"learning_rate": 1.5114981022549677e-05,
|
| 2574 |
+
"loss": 4.497,
|
| 2575 |
+
"step": 106250
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 2.1,
|
| 2579 |
+
"learning_rate": 1.5032898624955677e-05,
|
| 2580 |
+
"loss": 4.4993,
|
| 2581 |
+
"step": 106500
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 2.1,
|
| 2585 |
+
"learning_rate": 1.4950816227361674e-05,
|
| 2586 |
+
"loss": 4.5091,
|
| 2587 |
+
"step": 106750
|
| 2588 |
+
},
|
| 2589 |
+
{
|
| 2590 |
+
"epoch": 2.11,
|
| 2591 |
+
"learning_rate": 1.4868733829767676e-05,
|
| 2592 |
+
"loss": 4.5167,
|
| 2593 |
+
"step": 107000
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.11,
|
| 2597 |
+
"learning_rate": 1.4786651432173673e-05,
|
| 2598 |
+
"loss": 4.4561,
|
| 2599 |
+
"step": 107250
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.12,
|
| 2603 |
+
"learning_rate": 1.4704569034579675e-05,
|
| 2604 |
+
"loss": 4.5323,
|
| 2605 |
+
"step": 107500
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 2.12,
|
| 2609 |
+
"learning_rate": 1.4622486636985672e-05,
|
| 2610 |
+
"loss": 4.5174,
|
| 2611 |
+
"step": 107750
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 2.13,
|
| 2615 |
+
"learning_rate": 1.4540404239391672e-05,
|
| 2616 |
+
"loss": 4.5102,
|
| 2617 |
+
"step": 108000
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 2.13,
|
| 2621 |
+
"learning_rate": 1.445832184179767e-05,
|
| 2622 |
+
"loss": 4.4722,
|
| 2623 |
+
"step": 108250
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 2.14,
|
| 2627 |
+
"learning_rate": 1.437623944420367e-05,
|
| 2628 |
+
"loss": 4.4973,
|
| 2629 |
+
"step": 108500
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 2.14,
|
| 2633 |
+
"learning_rate": 1.4294157046609669e-05,
|
| 2634 |
+
"loss": 4.4885,
|
| 2635 |
+
"step": 108750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 2.15,
|
| 2639 |
+
"learning_rate": 1.421207464901567e-05,
|
| 2640 |
+
"loss": 4.4767,
|
| 2641 |
+
"step": 109000
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.15,
|
| 2645 |
+
"learning_rate": 1.4129992251421668e-05,
|
| 2646 |
+
"loss": 4.4758,
|
| 2647 |
+
"step": 109250
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 2.16,
|
| 2651 |
+
"learning_rate": 1.4047909853827667e-05,
|
| 2652 |
+
"loss": 4.4632,
|
| 2653 |
+
"step": 109500
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 2.16,
|
| 2657 |
+
"learning_rate": 1.3965827456233665e-05,
|
| 2658 |
+
"loss": 4.4848,
|
| 2659 |
+
"step": 109750
|
| 2660 |
+
},
|
| 2661 |
+
{
|
| 2662 |
+
"epoch": 2.17,
|
| 2663 |
+
"learning_rate": 1.3883745058639666e-05,
|
| 2664 |
+
"loss": 4.4566,
|
| 2665 |
+
"step": 110000
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 2.17,
|
| 2669 |
+
"learning_rate": 1.3801662661045664e-05,
|
| 2670 |
+
"loss": 4.4524,
|
| 2671 |
+
"step": 110250
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 2.18,
|
| 2675 |
+
"learning_rate": 1.3719580263451665e-05,
|
| 2676 |
+
"loss": 4.448,
|
| 2677 |
+
"step": 110500
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 2.18,
|
| 2681 |
+
"learning_rate": 1.3637497865857663e-05,
|
| 2682 |
+
"loss": 4.458,
|
| 2683 |
+
"step": 110750
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.19,
|
| 2687 |
+
"learning_rate": 1.3555415468263662e-05,
|
| 2688 |
+
"loss": 4.4448,
|
| 2689 |
+
"step": 111000
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 2.19,
|
| 2693 |
+
"learning_rate": 1.347333307066966e-05,
|
| 2694 |
+
"loss": 4.4719,
|
| 2695 |
+
"step": 111250
|
| 2696 |
+
},
|
| 2697 |
+
{
|
| 2698 |
+
"epoch": 2.2,
|
| 2699 |
+
"learning_rate": 1.3391250673075661e-05,
|
| 2700 |
+
"loss": 4.4535,
|
| 2701 |
+
"step": 111500
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 2.2,
|
| 2705 |
+
"learning_rate": 1.3309168275481659e-05,
|
| 2706 |
+
"loss": 4.4429,
|
| 2707 |
+
"step": 111750
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 2.21,
|
| 2711 |
+
"learning_rate": 1.322708587788766e-05,
|
| 2712 |
+
"loss": 4.4854,
|
| 2713 |
+
"step": 112000
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 2.21,
|
| 2717 |
+
"learning_rate": 1.3145003480293658e-05,
|
| 2718 |
+
"loss": 4.409,
|
| 2719 |
+
"step": 112250
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 2.22,
|
| 2723 |
+
"learning_rate": 1.3062921082699658e-05,
|
| 2724 |
+
"loss": 4.4335,
|
| 2725 |
+
"step": 112500
|
| 2726 |
+
}
|
| 2727 |
+
],
|
| 2728 |
+
"logging_steps": 250,
|
| 2729 |
+
"max_steps": 152286,
|
| 2730 |
+
"num_train_epochs": 3,
|
| 2731 |
+
"save_steps": 2048,
|
| 2732 |
+
"total_flos": 4.66845448223232e+17,
|
| 2733 |
+
"trial_name": null,
|
| 2734 |
+
"trial_params": null
|
| 2735 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f329752b7c2bc87d297d48f66104f72227f2dcee4f0e032a9725eb0ca5e2269f
|
| 3 |
+
size 3963
|