Uploaded new
Browse filesNew catalanqa checkpoint by casimiro for demo tests
- config.json +26 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +754 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "projecte-aina/roberta-base-ca-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"transformers_version": "4.6.1",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 50262
|
| 26 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c4a7dbbf176df46001b1fa313d38a3589c32d74bb339146e77e65ac13ccb5b
|
| 3 |
+
size 992555113
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fa65b6bbf442f1d37f4244830fd4a6e39d71632e36809763cede80960cf11b3
|
| 3 |
+
size 496304725
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caff97a5eaa28f200da70c082e0047055216280482309fe0108ebbb1a51a06ca
|
| 3 |
+
size 14647
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cd55648a76c3e9ba6f49dcfc24185d3721ba0e50b9bdd0e3a8ff96f6e783439
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "projecte-aina/roberta-base-ca-v2"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,754 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 87.64485843737634,
|
| 3 |
+
"best_model_checkpoint": "/home/ccasimiro/ccasimiro/berta/src/qa/roberta-base-ca-v2-qa/catalanqa/checkpoint-1134",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 5670,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 4.955908289241622e-05,
|
| 13 |
+
"loss": 5.04,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 4.9118165784832456e-05,
|
| 19 |
+
"loss": 3.614,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 4.8677248677248676e-05,
|
| 25 |
+
"loss": 3.1231,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.35,
|
| 30 |
+
"learning_rate": 4.82363315696649e-05,
|
| 31 |
+
"loss": 2.7369,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.44,
|
| 36 |
+
"learning_rate": 4.779541446208113e-05,
|
| 37 |
+
"loss": 2.3199,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.53,
|
| 42 |
+
"learning_rate": 4.7354497354497356e-05,
|
| 43 |
+
"loss": 2.0626,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.62,
|
| 48 |
+
"learning_rate": 4.691358024691358e-05,
|
| 49 |
+
"loss": 1.8434,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.71,
|
| 54 |
+
"learning_rate": 4.647266313932981e-05,
|
| 55 |
+
"loss": 1.5806,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.79,
|
| 60 |
+
"learning_rate": 4.603174603174603e-05,
|
| 61 |
+
"loss": 1.4498,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.88,
|
| 66 |
+
"learning_rate": 4.559082892416226e-05,
|
| 67 |
+
"loss": 1.2956,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.97,
|
| 72 |
+
"learning_rate": 4.5149911816578484e-05,
|
| 73 |
+
"loss": 1.1497,
|
| 74 |
+
"step": 550
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_exact_match": 69.11247803163445,
|
| 79 |
+
"eval_f1": 85.23057847114657,
|
| 80 |
+
"step": 567
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.06,
|
| 84 |
+
"learning_rate": 4.470899470899471e-05,
|
| 85 |
+
"loss": 0.9974,
|
| 86 |
+
"step": 600
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.15,
|
| 90 |
+
"learning_rate": 4.426807760141094e-05,
|
| 91 |
+
"loss": 0.9077,
|
| 92 |
+
"step": 650
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.23,
|
| 96 |
+
"learning_rate": 4.3827160493827164e-05,
|
| 97 |
+
"loss": 0.8397,
|
| 98 |
+
"step": 700
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.32,
|
| 102 |
+
"learning_rate": 4.3386243386243384e-05,
|
| 103 |
+
"loss": 0.7758,
|
| 104 |
+
"step": 750
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.41,
|
| 108 |
+
"learning_rate": 4.294532627865962e-05,
|
| 109 |
+
"loss": 0.7537,
|
| 110 |
+
"step": 800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.5,
|
| 114 |
+
"learning_rate": 4.250440917107584e-05,
|
| 115 |
+
"loss": 0.7319,
|
| 116 |
+
"step": 850
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.59,
|
| 120 |
+
"learning_rate": 4.2063492063492065e-05,
|
| 121 |
+
"loss": 0.7263,
|
| 122 |
+
"step": 900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.68,
|
| 126 |
+
"learning_rate": 4.162257495590829e-05,
|
| 127 |
+
"loss": 0.7032,
|
| 128 |
+
"step": 950
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.76,
|
| 132 |
+
"learning_rate": 4.118165784832452e-05,
|
| 133 |
+
"loss": 0.6714,
|
| 134 |
+
"step": 1000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.85,
|
| 138 |
+
"learning_rate": 4.074074074074074e-05,
|
| 139 |
+
"loss": 0.6854,
|
| 140 |
+
"step": 1050
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.94,
|
| 144 |
+
"learning_rate": 4.029982363315697e-05,
|
| 145 |
+
"loss": 0.6446,
|
| 146 |
+
"step": 1100
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.0,
|
| 150 |
+
"eval_exact_match": 73.85764499121265,
|
| 151 |
+
"eval_f1": 87.64485843737634,
|
| 152 |
+
"step": 1134
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.03,
|
| 156 |
+
"learning_rate": 3.985890652557319e-05,
|
| 157 |
+
"loss": 0.588,
|
| 158 |
+
"step": 1150
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.12,
|
| 162 |
+
"learning_rate": 3.941798941798942e-05,
|
| 163 |
+
"loss": 0.4666,
|
| 164 |
+
"step": 1200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.2,
|
| 168 |
+
"learning_rate": 3.8977072310405645e-05,
|
| 169 |
+
"loss": 0.4807,
|
| 170 |
+
"step": 1250
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.29,
|
| 174 |
+
"learning_rate": 3.853615520282187e-05,
|
| 175 |
+
"loss": 0.4549,
|
| 176 |
+
"step": 1300
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.38,
|
| 180 |
+
"learning_rate": 3.809523809523809e-05,
|
| 181 |
+
"loss": 0.4482,
|
| 182 |
+
"step": 1350
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.47,
|
| 186 |
+
"learning_rate": 3.7654320987654326e-05,
|
| 187 |
+
"loss": 0.4739,
|
| 188 |
+
"step": 1400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.56,
|
| 192 |
+
"learning_rate": 3.7213403880070546e-05,
|
| 193 |
+
"loss": 0.4336,
|
| 194 |
+
"step": 1450
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.65,
|
| 198 |
+
"learning_rate": 3.677248677248677e-05,
|
| 199 |
+
"loss": 0.3979,
|
| 200 |
+
"step": 1500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.73,
|
| 204 |
+
"learning_rate": 3.6331569664903e-05,
|
| 205 |
+
"loss": 0.5031,
|
| 206 |
+
"step": 1550
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.82,
|
| 210 |
+
"learning_rate": 3.5890652557319226e-05,
|
| 211 |
+
"loss": 0.4193,
|
| 212 |
+
"step": 1600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.91,
|
| 216 |
+
"learning_rate": 3.5449735449735446e-05,
|
| 217 |
+
"loss": 0.4714,
|
| 218 |
+
"step": 1650
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.0,
|
| 222 |
+
"learning_rate": 3.500881834215168e-05,
|
| 223 |
+
"loss": 0.416,
|
| 224 |
+
"step": 1700
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.0,
|
| 228 |
+
"eval_exact_match": 73.94551845342707,
|
| 229 |
+
"eval_f1": 87.39678260774708,
|
| 230 |
+
"step": 1701
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.09,
|
| 234 |
+
"learning_rate": 3.45679012345679e-05,
|
| 235 |
+
"loss": 0.2783,
|
| 236 |
+
"step": 1750
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.17,
|
| 240 |
+
"learning_rate": 3.412698412698413e-05,
|
| 241 |
+
"loss": 0.271,
|
| 242 |
+
"step": 1800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.26,
|
| 246 |
+
"learning_rate": 3.3686067019400353e-05,
|
| 247 |
+
"loss": 0.2807,
|
| 248 |
+
"step": 1850
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.35,
|
| 252 |
+
"learning_rate": 3.324514991181658e-05,
|
| 253 |
+
"loss": 0.3413,
|
| 254 |
+
"step": 1900
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.44,
|
| 258 |
+
"learning_rate": 3.280423280423281e-05,
|
| 259 |
+
"loss": 0.3236,
|
| 260 |
+
"step": 1950
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.53,
|
| 264 |
+
"learning_rate": 3.2363315696649034e-05,
|
| 265 |
+
"loss": 0.3034,
|
| 266 |
+
"step": 2000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.62,
|
| 270 |
+
"learning_rate": 3.1922398589065254e-05,
|
| 271 |
+
"loss": 0.3067,
|
| 272 |
+
"step": 2050
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.7,
|
| 276 |
+
"learning_rate": 3.148148148148148e-05,
|
| 277 |
+
"loss": 0.2978,
|
| 278 |
+
"step": 2100
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.79,
|
| 282 |
+
"learning_rate": 3.104056437389771e-05,
|
| 283 |
+
"loss": 0.3084,
|
| 284 |
+
"step": 2150
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.88,
|
| 288 |
+
"learning_rate": 3.0599647266313934e-05,
|
| 289 |
+
"loss": 0.3331,
|
| 290 |
+
"step": 2200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.97,
|
| 294 |
+
"learning_rate": 3.0158730158730158e-05,
|
| 295 |
+
"loss": 0.3132,
|
| 296 |
+
"step": 2250
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.0,
|
| 300 |
+
"eval_exact_match": 73.59402460456943,
|
| 301 |
+
"eval_f1": 87.53281609001948,
|
| 302 |
+
"step": 2268
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.06,
|
| 306 |
+
"learning_rate": 2.9717813051146388e-05,
|
| 307 |
+
"loss": 0.2315,
|
| 308 |
+
"step": 2300
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.14,
|
| 312 |
+
"learning_rate": 2.927689594356261e-05,
|
| 313 |
+
"loss": 0.2073,
|
| 314 |
+
"step": 2350
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.23,
|
| 318 |
+
"learning_rate": 2.8835978835978838e-05,
|
| 319 |
+
"loss": 0.1865,
|
| 320 |
+
"step": 2400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.32,
|
| 324 |
+
"learning_rate": 2.839506172839506e-05,
|
| 325 |
+
"loss": 0.1868,
|
| 326 |
+
"step": 2450
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.41,
|
| 330 |
+
"learning_rate": 2.795414462081129e-05,
|
| 331 |
+
"loss": 0.2252,
|
| 332 |
+
"step": 2500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.5,
|
| 336 |
+
"learning_rate": 2.7513227513227512e-05,
|
| 337 |
+
"loss": 0.2252,
|
| 338 |
+
"step": 2550
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.59,
|
| 342 |
+
"learning_rate": 2.7072310405643742e-05,
|
| 343 |
+
"loss": 0.198,
|
| 344 |
+
"step": 2600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.67,
|
| 348 |
+
"learning_rate": 2.6631393298059965e-05,
|
| 349 |
+
"loss": 0.2137,
|
| 350 |
+
"step": 2650
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.76,
|
| 354 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 355 |
+
"loss": 0.2006,
|
| 356 |
+
"step": 2700
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.85,
|
| 360 |
+
"learning_rate": 2.5749559082892416e-05,
|
| 361 |
+
"loss": 0.2478,
|
| 362 |
+
"step": 2750
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.94,
|
| 366 |
+
"learning_rate": 2.5308641975308646e-05,
|
| 367 |
+
"loss": 0.2094,
|
| 368 |
+
"step": 2800
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.0,
|
| 372 |
+
"eval_exact_match": 72.84710017574693,
|
| 373 |
+
"eval_f1": 87.02126420060829,
|
| 374 |
+
"step": 2835
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.03,
|
| 378 |
+
"learning_rate": 2.4867724867724866e-05,
|
| 379 |
+
"loss": 0.1825,
|
| 380 |
+
"step": 2850
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.11,
|
| 384 |
+
"learning_rate": 2.4426807760141093e-05,
|
| 385 |
+
"loss": 0.1354,
|
| 386 |
+
"step": 2900
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.2,
|
| 390 |
+
"learning_rate": 2.398589065255732e-05,
|
| 391 |
+
"loss": 0.1383,
|
| 392 |
+
"step": 2950
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.29,
|
| 396 |
+
"learning_rate": 2.3544973544973546e-05,
|
| 397 |
+
"loss": 0.1417,
|
| 398 |
+
"step": 3000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.38,
|
| 402 |
+
"learning_rate": 2.310405643738977e-05,
|
| 403 |
+
"loss": 0.174,
|
| 404 |
+
"step": 3050
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.47,
|
| 408 |
+
"learning_rate": 2.2663139329805996e-05,
|
| 409 |
+
"loss": 0.1297,
|
| 410 |
+
"step": 3100
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 5.56,
|
| 414 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 415 |
+
"loss": 0.1254,
|
| 416 |
+
"step": 3150
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.64,
|
| 420 |
+
"learning_rate": 2.1781305114638447e-05,
|
| 421 |
+
"loss": 0.1467,
|
| 422 |
+
"step": 3200
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.73,
|
| 426 |
+
"learning_rate": 2.1340388007054674e-05,
|
| 427 |
+
"loss": 0.1429,
|
| 428 |
+
"step": 3250
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.82,
|
| 432 |
+
"learning_rate": 2.08994708994709e-05,
|
| 433 |
+
"loss": 0.1401,
|
| 434 |
+
"step": 3300
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.91,
|
| 438 |
+
"learning_rate": 2.0458553791887124e-05,
|
| 439 |
+
"loss": 0.1309,
|
| 440 |
+
"step": 3350
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.0,
|
| 444 |
+
"learning_rate": 2.001763668430335e-05,
|
| 445 |
+
"loss": 0.1286,
|
| 446 |
+
"step": 3400
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 6.0,
|
| 450 |
+
"eval_exact_match": 73.76977152899825,
|
| 451 |
+
"eval_f1": 87.38988637413004,
|
| 452 |
+
"step": 3402
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 6.08,
|
| 456 |
+
"learning_rate": 1.9576719576719577e-05,
|
| 457 |
+
"loss": 0.102,
|
| 458 |
+
"step": 3450
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.17,
|
| 462 |
+
"learning_rate": 1.91358024691358e-05,
|
| 463 |
+
"loss": 0.1046,
|
| 464 |
+
"step": 3500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.26,
|
| 468 |
+
"learning_rate": 1.8694885361552028e-05,
|
| 469 |
+
"loss": 0.0967,
|
| 470 |
+
"step": 3550
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.35,
|
| 474 |
+
"learning_rate": 1.8253968253968254e-05,
|
| 475 |
+
"loss": 0.1127,
|
| 476 |
+
"step": 3600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 6.44,
|
| 480 |
+
"learning_rate": 1.781305114638448e-05,
|
| 481 |
+
"loss": 0.093,
|
| 482 |
+
"step": 3650
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.53,
|
| 486 |
+
"learning_rate": 1.7372134038800705e-05,
|
| 487 |
+
"loss": 0.1085,
|
| 488 |
+
"step": 3700
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.61,
|
| 492 |
+
"learning_rate": 1.693121693121693e-05,
|
| 493 |
+
"loss": 0.0913,
|
| 494 |
+
"step": 3750
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.7,
|
| 498 |
+
"learning_rate": 1.6490299823633158e-05,
|
| 499 |
+
"loss": 0.1008,
|
| 500 |
+
"step": 3800
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.79,
|
| 504 |
+
"learning_rate": 1.604938271604938e-05,
|
| 505 |
+
"loss": 0.1191,
|
| 506 |
+
"step": 3850
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.88,
|
| 510 |
+
"learning_rate": 1.560846560846561e-05,
|
| 511 |
+
"loss": 0.095,
|
| 512 |
+
"step": 3900
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.97,
|
| 516 |
+
"learning_rate": 1.5167548500881834e-05,
|
| 517 |
+
"loss": 0.1145,
|
| 518 |
+
"step": 3950
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 7.0,
|
| 522 |
+
"eval_exact_match": 73.94551845342707,
|
| 523 |
+
"eval_f1": 87.51076671024968,
|
| 524 |
+
"step": 3969
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 7.05,
|
| 528 |
+
"learning_rate": 1.472663139329806e-05,
|
| 529 |
+
"loss": 0.0907,
|
| 530 |
+
"step": 4000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 7.14,
|
| 534 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 535 |
+
"loss": 0.0702,
|
| 536 |
+
"step": 4050
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 7.23,
|
| 540 |
+
"learning_rate": 1.384479717813051e-05,
|
| 541 |
+
"loss": 0.0683,
|
| 542 |
+
"step": 4100
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 7.32,
|
| 546 |
+
"learning_rate": 1.3403880070546737e-05,
|
| 547 |
+
"loss": 0.0877,
|
| 548 |
+
"step": 4150
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.41,
|
| 552 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 553 |
+
"loss": 0.085,
|
| 554 |
+
"step": 4200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 7.5,
|
| 558 |
+
"learning_rate": 1.252204585537919e-05,
|
| 559 |
+
"loss": 0.0673,
|
| 560 |
+
"step": 4250
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 7.58,
|
| 564 |
+
"learning_rate": 1.2081128747795414e-05,
|
| 565 |
+
"loss": 0.0664,
|
| 566 |
+
"step": 4300
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 7.67,
|
| 570 |
+
"learning_rate": 1.164021164021164e-05,
|
| 571 |
+
"loss": 0.0984,
|
| 572 |
+
"step": 4350
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 7.76,
|
| 576 |
+
"learning_rate": 1.1199294532627866e-05,
|
| 577 |
+
"loss": 0.0635,
|
| 578 |
+
"step": 4400
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 7.85,
|
| 582 |
+
"learning_rate": 1.0758377425044091e-05,
|
| 583 |
+
"loss": 0.0866,
|
| 584 |
+
"step": 4450
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 7.94,
|
| 588 |
+
"learning_rate": 1.0317460317460318e-05,
|
| 589 |
+
"loss": 0.0744,
|
| 590 |
+
"step": 4500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.0,
|
| 594 |
+
"eval_exact_match": 73.85764499121265,
|
| 595 |
+
"eval_f1": 87.23571814342841,
|
| 596 |
+
"step": 4536
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 8.02,
|
| 600 |
+
"learning_rate": 9.876543209876543e-06,
|
| 601 |
+
"loss": 0.0788,
|
| 602 |
+
"step": 4550
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 8.11,
|
| 606 |
+
"learning_rate": 9.435626102292768e-06,
|
| 607 |
+
"loss": 0.0556,
|
| 608 |
+
"step": 4600
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 8.2,
|
| 612 |
+
"learning_rate": 8.994708994708995e-06,
|
| 613 |
+
"loss": 0.0415,
|
| 614 |
+
"step": 4650
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 8.29,
|
| 618 |
+
"learning_rate": 8.55379188712522e-06,
|
| 619 |
+
"loss": 0.052,
|
| 620 |
+
"step": 4700
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 8.38,
|
| 624 |
+
"learning_rate": 8.112874779541445e-06,
|
| 625 |
+
"loss": 0.0636,
|
| 626 |
+
"step": 4750
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 8.47,
|
| 630 |
+
"learning_rate": 7.671957671957672e-06,
|
| 631 |
+
"loss": 0.0481,
|
| 632 |
+
"step": 4800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 8.55,
|
| 636 |
+
"learning_rate": 7.231040564373897e-06,
|
| 637 |
+
"loss": 0.0545,
|
| 638 |
+
"step": 4850
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 8.64,
|
| 642 |
+
"learning_rate": 6.790123456790123e-06,
|
| 643 |
+
"loss": 0.0597,
|
| 644 |
+
"step": 4900
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 8.73,
|
| 648 |
+
"learning_rate": 6.349206349206349e-06,
|
| 649 |
+
"loss": 0.0437,
|
| 650 |
+
"step": 4950
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 8.82,
|
| 654 |
+
"learning_rate": 5.908289241622575e-06,
|
| 655 |
+
"loss": 0.0722,
|
| 656 |
+
"step": 5000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 8.91,
|
| 660 |
+
"learning_rate": 5.4673721340388e-06,
|
| 661 |
+
"loss": 0.062,
|
| 662 |
+
"step": 5050
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 8.99,
|
| 666 |
+
"learning_rate": 5.026455026455026e-06,
|
| 667 |
+
"loss": 0.0719,
|
| 668 |
+
"step": 5100
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 9.0,
|
| 672 |
+
"eval_exact_match": 74.07732864674868,
|
| 673 |
+
"eval_f1": 87.42888206161075,
|
| 674 |
+
"step": 5103
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.08,
|
| 678 |
+
"learning_rate": 4.585537918871252e-06,
|
| 679 |
+
"loss": 0.0346,
|
| 680 |
+
"step": 5150
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 9.17,
|
| 684 |
+
"learning_rate": 4.144620811287478e-06,
|
| 685 |
+
"loss": 0.0373,
|
| 686 |
+
"step": 5200
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 9.26,
|
| 690 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 691 |
+
"loss": 0.0333,
|
| 692 |
+
"step": 5250
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 9.35,
|
| 696 |
+
"learning_rate": 3.2627865961199293e-06,
|
| 697 |
+
"loss": 0.0384,
|
| 698 |
+
"step": 5300
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 9.44,
|
| 702 |
+
"learning_rate": 2.8218694885361552e-06,
|
| 703 |
+
"loss": 0.0413,
|
| 704 |
+
"step": 5350
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 9.52,
|
| 708 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 709 |
+
"loss": 0.0511,
|
| 710 |
+
"step": 5400
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 9.61,
|
| 714 |
+
"learning_rate": 1.9400352733686067e-06,
|
| 715 |
+
"loss": 0.0453,
|
| 716 |
+
"step": 5450
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 9.7,
|
| 720 |
+
"learning_rate": 1.4991181657848325e-06,
|
| 721 |
+
"loss": 0.0422,
|
| 722 |
+
"step": 5500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 9.79,
|
| 726 |
+
"learning_rate": 1.0582010582010582e-06,
|
| 727 |
+
"loss": 0.0572,
|
| 728 |
+
"step": 5550
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 9.88,
|
| 732 |
+
"learning_rate": 6.17283950617284e-07,
|
| 733 |
+
"loss": 0.0494,
|
| 734 |
+
"step": 5600
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 9.96,
|
| 738 |
+
"learning_rate": 1.763668430335097e-07,
|
| 739 |
+
"loss": 0.0444,
|
| 740 |
+
"step": 5650
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 10.0,
|
| 744 |
+
"eval_exact_match": 74.34094903339192,
|
| 745 |
+
"eval_f1": 87.50452307749782,
|
| 746 |
+
"step": 5670
|
| 747 |
+
}
|
| 748 |
+
],
|
| 749 |
+
"max_steps": 5670,
|
| 750 |
+
"num_train_epochs": 10,
|
| 751 |
+
"total_flos": 6912296207806464.0,
|
| 752 |
+
"trial_name": null,
|
| 753 |
+
"trial_params": null
|
| 754 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f1353cbc61d08a06977fb0569fb72c8aa15755a963d2ec5ae66906f352d035b
|
| 3 |
+
size 2543
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|