Initial upload of multiple checkpoints
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-100000/config.json +26 -0
- checkpoint-100000/merges.txt +0 -0
- checkpoint-100000/model.safetensors +3 -0
- checkpoint-100000/optimizer.pt +3 -0
- checkpoint-100000/rng_state.pth +3 -0
- checkpoint-100000/scaler.pt +3 -0
- checkpoint-100000/scheduler.pt +3 -0
- checkpoint-100000/special_tokens_map.json +51 -0
- checkpoint-100000/tokenizer.json +0 -0
- checkpoint-100000/tokenizer_config.json +58 -0
- checkpoint-100000/trainer_state.json +1434 -0
- checkpoint-100000/training_args.bin +3 -0
- checkpoint-100000/vocab.json +0 -0
- checkpoint-20000/config.json +26 -0
- checkpoint-20000/merges.txt +0 -0
- checkpoint-20000/model.safetensors +3 -0
- checkpoint-20000/optimizer.pt +3 -0
- checkpoint-20000/rng_state.pth +3 -0
- checkpoint-20000/scaler.pt +3 -0
- checkpoint-20000/scheduler.pt +3 -0
- checkpoint-20000/special_tokens_map.json +51 -0
- checkpoint-20000/tokenizer.json +0 -0
- checkpoint-20000/tokenizer_config.json +58 -0
- checkpoint-20000/trainer_state.json +314 -0
- checkpoint-20000/training_args.bin +3 -0
- checkpoint-20000/vocab.json +0 -0
- checkpoint-40000/config.json +26 -0
- checkpoint-40000/merges.txt +0 -0
- checkpoint-40000/model.safetensors +3 -0
- checkpoint-40000/optimizer.pt +3 -0
- checkpoint-40000/rng_state.pth +3 -0
- checkpoint-40000/scaler.pt +3 -0
- checkpoint-40000/scheduler.pt +3 -0
- checkpoint-40000/special_tokens_map.json +51 -0
- checkpoint-40000/tokenizer.json +0 -0
- checkpoint-40000/tokenizer_config.json +58 -0
- checkpoint-40000/trainer_state.json +594 -0
- checkpoint-40000/training_args.bin +3 -0
- checkpoint-40000/vocab.json +0 -0
- checkpoint-60000/config.json +26 -0
- checkpoint-60000/merges.txt +0 -0
- checkpoint-60000/model.safetensors +3 -0
- checkpoint-60000/optimizer.pt +3 -0
- checkpoint-60000/rng_state.pth +3 -0
- checkpoint-60000/scaler.pt +3 -0
- checkpoint-60000/scheduler.pt +3 -0
- checkpoint-60000/special_tokens_map.json +51 -0
- checkpoint-60000/tokenizer.json +0 -0
- checkpoint-60000/tokenizer_config.json +58 -0
- checkpoint-60000/trainer_state.json +874 -0
checkpoint-100000/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": 514,
|
| 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": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13e43d94f1d0a5a336e93f07d556a347973aae7c0a70c12c164ab7d7255796f2
|
| 3 |
+
size 334030264
|
checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a533719563629d9cb9dc3d1467c4733984b8dca487e258601002b6399bc056e1
|
| 3 |
+
size 668124218
|
checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0367f51d3010e4f2736a19f2ffac973b5e063ce09ce6150cfd65ab79e9a15afb
|
| 3 |
+
size 14244
|
checkpoint-100000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a97fbccab8b02a2025d7c1525a24de5f98f4d5a4343087384c1419bada42f7
|
| 3 |
+
size 988
|
checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abecbcba530303988e8720011dcd4151f31dcec56f61583d3ef01382162cc5b9
|
| 3 |
+
size 1064
|
checkpoint-100000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-100000/trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.91957811470007,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3295978905735003,
|
| 14 |
+
"grad_norm": 2.8918700218200684,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.1735,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6591957811470006,
|
| 21 |
+
"grad_norm": 2.0813119411468506,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 8.4577,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.988793671720501,
|
| 28 |
+
"grad_norm": 1.871568202972412,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 7.6313,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.3183915622940012,
|
| 35 |
+
"grad_norm": 1.7127728462219238,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 7.3405,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.6479894528675016,
|
| 42 |
+
"grad_norm": 1.7611004114151,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 7.1579,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.977587343441002,
|
| 49 |
+
"grad_norm": 1.7559301853179932,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 7.0353,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.3071852340145025,
|
| 56 |
+
"grad_norm": 2.062741994857788,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 6.949,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.6367831245880025,
|
| 63 |
+
"grad_norm": 2.037240505218506,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 6.8905,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.966381015161503,
|
| 70 |
+
"grad_norm": 2.732247829437256,
|
| 71 |
+
"learning_rate": 4.5e-05,
|
| 72 |
+
"loss": 6.8433,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.2959789057350033,
|
| 77 |
+
"grad_norm": 2.648927927017212,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 6.7753,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.6255767963085037,
|
| 84 |
+
"grad_norm": 3.1528918743133545,
|
| 85 |
+
"learning_rate": 5.500000000000001e-05,
|
| 86 |
+
"loss": 6.747,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.955174686882004,
|
| 91 |
+
"grad_norm": 2.9101691246032715,
|
| 92 |
+
"learning_rate": 6e-05,
|
| 93 |
+
"loss": 6.7081,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.284772577455504,
|
| 98 |
+
"grad_norm": 2.407719612121582,
|
| 99 |
+
"learning_rate": 6.499000000000001e-05,
|
| 100 |
+
"loss": 6.6724,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.614370468029005,
|
| 105 |
+
"grad_norm": 1.8148102760314941,
|
| 106 |
+
"learning_rate": 6.999e-05,
|
| 107 |
+
"loss": 6.6584,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.943968358602505,
|
| 112 |
+
"grad_norm": 2.6724727153778076,
|
| 113 |
+
"learning_rate": 7.499e-05,
|
| 114 |
+
"loss": 6.6439,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.273566249176005,
|
| 119 |
+
"grad_norm": 2.199885368347168,
|
| 120 |
+
"learning_rate": 7.999000000000001e-05,
|
| 121 |
+
"loss": 6.592,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.603164139749506,
|
| 126 |
+
"grad_norm": 2.2242558002471924,
|
| 127 |
+
"learning_rate": 8.498e-05,
|
| 128 |
+
"loss": 6.5687,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.932762030323006,
|
| 133 |
+
"grad_norm": 3.0547144412994385,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 6.5339,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.262359920896507,
|
| 140 |
+
"grad_norm": 3.8027408123016357,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 6.4818,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.591957811470007,
|
| 147 |
+
"grad_norm": 2.3049635887145996,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 6.392,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.921555702043507,
|
| 154 |
+
"grad_norm": 3.5188333988189697,
|
| 155 |
+
"learning_rate": 9.944777777777778e-05,
|
| 156 |
+
"loss": 6.2095,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.251153592617007,
|
| 161 |
+
"grad_norm": 5.0908050537109375,
|
| 162 |
+
"learning_rate": 9.889222222222223e-05,
|
| 163 |
+
"loss": 5.8004,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.580751483190507,
|
| 168 |
+
"grad_norm": 4.9945068359375,
|
| 169 |
+
"learning_rate": 9.833777777777779e-05,
|
| 170 |
+
"loss": 5.3376,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.910349373764008,
|
| 175 |
+
"grad_norm": 4.765307426452637,
|
| 176 |
+
"learning_rate": 9.778222222222222e-05,
|
| 177 |
+
"loss": 4.9592,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 8.23994726433751,
|
| 182 |
+
"grad_norm": 4.015578269958496,
|
| 183 |
+
"learning_rate": 9.722666666666666e-05,
|
| 184 |
+
"loss": 4.5913,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.569545154911008,
|
| 189 |
+
"grad_norm": 4.644675254821777,
|
| 190 |
+
"learning_rate": 9.667111111111111e-05,
|
| 191 |
+
"loss": 4.3206,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.899143045484509,
|
| 196 |
+
"grad_norm": 3.8366589546203613,
|
| 197 |
+
"learning_rate": 9.611555555555556e-05,
|
| 198 |
+
"loss": 4.1122,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 9.22874093605801,
|
| 203 |
+
"grad_norm": 4.115426540374756,
|
| 204 |
+
"learning_rate": 9.556111111111112e-05,
|
| 205 |
+
"loss": 3.8972,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.558338826631509,
|
| 210 |
+
"grad_norm": 4.137101650238037,
|
| 211 |
+
"learning_rate": 9.500555555555555e-05,
|
| 212 |
+
"loss": 3.7381,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.88793671720501,
|
| 217 |
+
"grad_norm": 5.157057285308838,
|
| 218 |
+
"learning_rate": 9.445e-05,
|
| 219 |
+
"loss": 3.6142,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 10.21753460777851,
|
| 224 |
+
"grad_norm": 3.9190354347229004,
|
| 225 |
+
"learning_rate": 9.389444444444446e-05,
|
| 226 |
+
"loss": 3.4768,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.54713249835201,
|
| 231 |
+
"grad_norm": 3.799747943878174,
|
| 232 |
+
"learning_rate": 9.333888888888889e-05,
|
| 233 |
+
"loss": 3.3694,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.87673038892551,
|
| 238 |
+
"grad_norm": 4.951575756072998,
|
| 239 |
+
"learning_rate": 9.278333333333333e-05,
|
| 240 |
+
"loss": 3.2834,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 11.206328279499012,
|
| 245 |
+
"grad_norm": 3.807826042175293,
|
| 246 |
+
"learning_rate": 9.222777777777778e-05,
|
| 247 |
+
"loss": 3.176,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.53592617007251,
|
| 252 |
+
"grad_norm": 4.53897762298584,
|
| 253 |
+
"learning_rate": 9.167222222222223e-05,
|
| 254 |
+
"loss": 3.096,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.865524060646012,
|
| 259 |
+
"grad_norm": 4.1547980308532715,
|
| 260 |
+
"learning_rate": 9.111777777777779e-05,
|
| 261 |
+
"loss": 3.0208,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 12.195121951219512,
|
| 266 |
+
"grad_norm": 4.5414719581604,
|
| 267 |
+
"learning_rate": 9.056222222222222e-05,
|
| 268 |
+
"loss": 2.9412,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.524719841793013,
|
| 273 |
+
"grad_norm": 4.638998508453369,
|
| 274 |
+
"learning_rate": 9.000666666666667e-05,
|
| 275 |
+
"loss": 2.8768,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.854317732366512,
|
| 280 |
+
"grad_norm": 3.492238759994507,
|
| 281 |
+
"learning_rate": 8.945111111111112e-05,
|
| 282 |
+
"loss": 2.8319,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 13.183915622940013,
|
| 287 |
+
"grad_norm": 3.963812828063965,
|
| 288 |
+
"learning_rate": 8.889666666666668e-05,
|
| 289 |
+
"loss": 2.7481,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.513513513513514,
|
| 294 |
+
"grad_norm": 4.802724361419678,
|
| 295 |
+
"learning_rate": 8.834111111111112e-05,
|
| 296 |
+
"loss": 2.7044,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.843111404087013,
|
| 301 |
+
"grad_norm": 4.897942066192627,
|
| 302 |
+
"learning_rate": 8.778555555555555e-05,
|
| 303 |
+
"loss": 2.6523,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 14.172709294660514,
|
| 308 |
+
"grad_norm": 4.577375411987305,
|
| 309 |
+
"learning_rate": 8.723e-05,
|
| 310 |
+
"loss": 2.6131,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.502307185234015,
|
| 315 |
+
"grad_norm": 4.424295902252197,
|
| 316 |
+
"learning_rate": 8.667444444444444e-05,
|
| 317 |
+
"loss": 2.5573,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 14.831905075807516,
|
| 322 |
+
"grad_norm": 4.2922749519348145,
|
| 323 |
+
"learning_rate": 8.612e-05,
|
| 324 |
+
"loss": 2.5337,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 15.161502966381015,
|
| 329 |
+
"grad_norm": 4.366146564483643,
|
| 330 |
+
"learning_rate": 8.556444444444445e-05,
|
| 331 |
+
"loss": 2.4788,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.491100856954516,
|
| 336 |
+
"grad_norm": 4.874686241149902,
|
| 337 |
+
"learning_rate": 8.50088888888889e-05,
|
| 338 |
+
"loss": 2.4399,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.820698747528017,
|
| 343 |
+
"grad_norm": 5.1893463134765625,
|
| 344 |
+
"learning_rate": 8.445333333333333e-05,
|
| 345 |
+
"loss": 2.4304,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.150296638101516,
|
| 350 |
+
"grad_norm": 4.169196605682373,
|
| 351 |
+
"learning_rate": 8.389888888888889e-05,
|
| 352 |
+
"loss": 2.3779,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.47989452867502,
|
| 357 |
+
"grad_norm": 4.332625865936279,
|
| 358 |
+
"learning_rate": 8.334333333333334e-05,
|
| 359 |
+
"loss": 2.3538,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.809492419248517,
|
| 364 |
+
"grad_norm": 5.98911190032959,
|
| 365 |
+
"learning_rate": 8.278777777777779e-05,
|
| 366 |
+
"loss": 2.3304,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.139090309822016,
|
| 371 |
+
"grad_norm": 4.644032001495361,
|
| 372 |
+
"learning_rate": 8.223222222222223e-05,
|
| 373 |
+
"loss": 2.3024,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 17.46868820039552,
|
| 378 |
+
"grad_norm": 4.4497971534729,
|
| 379 |
+
"learning_rate": 8.167777777777778e-05,
|
| 380 |
+
"loss": 2.2653,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.798286090969018,
|
| 385 |
+
"grad_norm": 3.7030065059661865,
|
| 386 |
+
"learning_rate": 8.112222222222222e-05,
|
| 387 |
+
"loss": 2.2525,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 18.127883981542517,
|
| 392 |
+
"grad_norm": 4.448596000671387,
|
| 393 |
+
"learning_rate": 8.056777777777779e-05,
|
| 394 |
+
"loss": 2.2154,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 18.45748187211602,
|
| 399 |
+
"grad_norm": 4.464804649353027,
|
| 400 |
+
"learning_rate": 8.001222222222222e-05,
|
| 401 |
+
"loss": 2.2012,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.78707976268952,
|
| 406 |
+
"grad_norm": 4.686955451965332,
|
| 407 |
+
"learning_rate": 7.945666666666667e-05,
|
| 408 |
+
"loss": 2.1827,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 19.116677653263018,
|
| 413 |
+
"grad_norm": 3.8840394020080566,
|
| 414 |
+
"learning_rate": 7.890111111111111e-05,
|
| 415 |
+
"loss": 2.1409,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 19.44627554383652,
|
| 420 |
+
"grad_norm": 3.527129888534546,
|
| 421 |
+
"learning_rate": 7.834555555555556e-05,
|
| 422 |
+
"loss": 2.1215,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.77587343441002,
|
| 427 |
+
"grad_norm": 5.817971706390381,
|
| 428 |
+
"learning_rate": 7.779000000000001e-05,
|
| 429 |
+
"loss": 2.1161,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 20.10547132498352,
|
| 434 |
+
"grad_norm": 5.153094291687012,
|
| 435 |
+
"learning_rate": 7.723444444444444e-05,
|
| 436 |
+
"loss": 2.0967,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 20.43506921555702,
|
| 441 |
+
"grad_norm": 5.022122859954834,
|
| 442 |
+
"learning_rate": 7.667888888888889e-05,
|
| 443 |
+
"loss": 2.0789,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.76466710613052,
|
| 448 |
+
"grad_norm": 4.343278884887695,
|
| 449 |
+
"learning_rate": 7.612444444444444e-05,
|
| 450 |
+
"loss": 2.0725,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 21.09426499670402,
|
| 455 |
+
"grad_norm": 5.50627326965332,
|
| 456 |
+
"learning_rate": 7.556888888888889e-05,
|
| 457 |
+
"loss": 2.0538,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 21.423862887277522,
|
| 462 |
+
"grad_norm": 4.042550563812256,
|
| 463 |
+
"learning_rate": 7.501333333333333e-05,
|
| 464 |
+
"loss": 2.0334,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.75346077785102,
|
| 469 |
+
"grad_norm": 5.352642059326172,
|
| 470 |
+
"learning_rate": 7.445777777777778e-05,
|
| 471 |
+
"loss": 2.0204,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 22.08305866842452,
|
| 476 |
+
"grad_norm": 4.7281494140625,
|
| 477 |
+
"learning_rate": 7.390333333333333e-05,
|
| 478 |
+
"loss": 2.0143,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 22.412656558998023,
|
| 483 |
+
"grad_norm": 5.191075801849365,
|
| 484 |
+
"learning_rate": 7.334777777777778e-05,
|
| 485 |
+
"loss": 1.9848,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.742254449571522,
|
| 490 |
+
"grad_norm": 3.772347927093506,
|
| 491 |
+
"learning_rate": 7.279222222222222e-05,
|
| 492 |
+
"loss": 1.9792,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 23.071852340145025,
|
| 497 |
+
"grad_norm": 4.231102466583252,
|
| 498 |
+
"learning_rate": 7.223666666666667e-05,
|
| 499 |
+
"loss": 1.9795,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 23.401450230718524,
|
| 504 |
+
"grad_norm": 4.547638416290283,
|
| 505 |
+
"learning_rate": 7.168222222222223e-05,
|
| 506 |
+
"loss": 1.943,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.731048121292023,
|
| 511 |
+
"grad_norm": 4.105598449707031,
|
| 512 |
+
"learning_rate": 7.112666666666668e-05,
|
| 513 |
+
"loss": 1.9403,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 24.060646011865526,
|
| 518 |
+
"grad_norm": 4.19888973236084,
|
| 519 |
+
"learning_rate": 7.057222222222223e-05,
|
| 520 |
+
"loss": 1.9306,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 24.390243902439025,
|
| 525 |
+
"grad_norm": 5.557919979095459,
|
| 526 |
+
"learning_rate": 7.001666666666667e-05,
|
| 527 |
+
"loss": 1.9055,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 24.719841793012524,
|
| 532 |
+
"grad_norm": 4.575863838195801,
|
| 533 |
+
"learning_rate": 6.946111111111111e-05,
|
| 534 |
+
"loss": 1.8855,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 25.049439683586026,
|
| 539 |
+
"grad_norm": 5.226344108581543,
|
| 540 |
+
"learning_rate": 6.890555555555556e-05,
|
| 541 |
+
"loss": 1.8906,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 25.379037574159526,
|
| 546 |
+
"grad_norm": 4.725679874420166,
|
| 547 |
+
"learning_rate": 6.835000000000001e-05,
|
| 548 |
+
"loss": 1.8643,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 25.708635464733025,
|
| 553 |
+
"grad_norm": 4.374075412750244,
|
| 554 |
+
"learning_rate": 6.779444444444444e-05,
|
| 555 |
+
"loss": 1.8558,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 26.038233355306527,
|
| 560 |
+
"grad_norm": 5.11503267288208,
|
| 561 |
+
"learning_rate": 6.72388888888889e-05,
|
| 562 |
+
"loss": 1.8685,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 26.367831245880026,
|
| 567 |
+
"grad_norm": 4.175240993499756,
|
| 568 |
+
"learning_rate": 6.668333333333333e-05,
|
| 569 |
+
"loss": 1.834,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 26.697429136453525,
|
| 574 |
+
"grad_norm": 5.351263999938965,
|
| 575 |
+
"learning_rate": 6.61288888888889e-05,
|
| 576 |
+
"loss": 1.8337,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 27.027027027027028,
|
| 581 |
+
"grad_norm": 4.664134979248047,
|
| 582 |
+
"learning_rate": 6.557333333333332e-05,
|
| 583 |
+
"loss": 1.8419,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 27.356624917600527,
|
| 588 |
+
"grad_norm": 4.658705711364746,
|
| 589 |
+
"learning_rate": 6.501777777777777e-05,
|
| 590 |
+
"loss": 1.7938,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 27.686222808174026,
|
| 595 |
+
"grad_norm": 4.4617228507995605,
|
| 596 |
+
"learning_rate": 6.446222222222223e-05,
|
| 597 |
+
"loss": 1.8047,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 28.01582069874753,
|
| 602 |
+
"grad_norm": 4.475608825683594,
|
| 603 |
+
"learning_rate": 6.390666666666668e-05,
|
| 604 |
+
"loss": 1.7869,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 28.345418589321028,
|
| 609 |
+
"grad_norm": 4.420760631561279,
|
| 610 |
+
"learning_rate": 6.335222222222222e-05,
|
| 611 |
+
"loss": 1.7748,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 28.675016479894527,
|
| 616 |
+
"grad_norm": 5.114872455596924,
|
| 617 |
+
"learning_rate": 6.279666666666667e-05,
|
| 618 |
+
"loss": 1.7581,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 29.00461437046803,
|
| 623 |
+
"grad_norm": 3.7333712577819824,
|
| 624 |
+
"learning_rate": 6.224111111111112e-05,
|
| 625 |
+
"loss": 1.768,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 29.33421226104153,
|
| 630 |
+
"grad_norm": 4.306798934936523,
|
| 631 |
+
"learning_rate": 6.168555555555557e-05,
|
| 632 |
+
"loss": 1.7278,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 29.66381015161503,
|
| 637 |
+
"grad_norm": 4.891313552856445,
|
| 638 |
+
"learning_rate": 6.113111111111111e-05,
|
| 639 |
+
"loss": 1.7436,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 29.99340804218853,
|
| 644 |
+
"grad_norm": 4.63929557800293,
|
| 645 |
+
"learning_rate": 6.057555555555556e-05,
|
| 646 |
+
"loss": 1.7448,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 30.32300593276203,
|
| 651 |
+
"grad_norm": 4.462540149688721,
|
| 652 |
+
"learning_rate": 6.0021111111111116e-05,
|
| 653 |
+
"loss": 1.7059,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 30.652603823335532,
|
| 658 |
+
"grad_norm": 4.313077449798584,
|
| 659 |
+
"learning_rate": 5.9465555555555567e-05,
|
| 660 |
+
"loss": 1.7273,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 30.98220171390903,
|
| 665 |
+
"grad_norm": 3.960693359375,
|
| 666 |
+
"learning_rate": 5.891e-05,
|
| 667 |
+
"loss": 1.7157,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 31.31179960448253,
|
| 672 |
+
"grad_norm": 4.755917549133301,
|
| 673 |
+
"learning_rate": 5.835444444444445e-05,
|
| 674 |
+
"loss": 1.6931,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 31.641397495056033,
|
| 679 |
+
"grad_norm": 4.8950042724609375,
|
| 680 |
+
"learning_rate": 5.779888888888889e-05,
|
| 681 |
+
"loss": 1.6889,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 31.970995385629532,
|
| 686 |
+
"grad_norm": 3.8848912715911865,
|
| 687 |
+
"learning_rate": 5.7243333333333335e-05,
|
| 688 |
+
"loss": 1.6881,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 32.30059327620303,
|
| 693 |
+
"grad_norm": 4.386871337890625,
|
| 694 |
+
"learning_rate": 5.6687777777777785e-05,
|
| 695 |
+
"loss": 1.6634,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 32.630191166776534,
|
| 700 |
+
"grad_norm": 4.7473464012146,
|
| 701 |
+
"learning_rate": 5.613222222222222e-05,
|
| 702 |
+
"loss": 1.6547,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 32.95978905735004,
|
| 707 |
+
"grad_norm": 4.609119892120361,
|
| 708 |
+
"learning_rate": 5.5577777777777784e-05,
|
| 709 |
+
"loss": 1.6622,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 33.28938694792353,
|
| 714 |
+
"grad_norm": 4.484665393829346,
|
| 715 |
+
"learning_rate": 5.502222222222222e-05,
|
| 716 |
+
"loss": 1.6462,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 33.618984838497035,
|
| 721 |
+
"grad_norm": 4.362062931060791,
|
| 722 |
+
"learning_rate": 5.4466666666666665e-05,
|
| 723 |
+
"loss": 1.638,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 33.94858272907054,
|
| 728 |
+
"grad_norm": 5.697278022766113,
|
| 729 |
+
"learning_rate": 5.3911111111111115e-05,
|
| 730 |
+
"loss": 1.6494,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 34.27818061964403,
|
| 735 |
+
"grad_norm": 5.001323223114014,
|
| 736 |
+
"learning_rate": 5.3356666666666663e-05,
|
| 737 |
+
"loss": 1.6304,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 34.607778510217535,
|
| 742 |
+
"grad_norm": 4.780933856964111,
|
| 743 |
+
"learning_rate": 5.2801111111111114e-05,
|
| 744 |
+
"loss": 1.6214,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 34.93737640079104,
|
| 749 |
+
"grad_norm": 4.25840425491333,
|
| 750 |
+
"learning_rate": 5.224555555555556e-05,
|
| 751 |
+
"loss": 1.6209,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 35.266974291364534,
|
| 756 |
+
"grad_norm": 3.9229302406311035,
|
| 757 |
+
"learning_rate": 5.169000000000001e-05,
|
| 758 |
+
"loss": 1.5934,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 35.596572181938036,
|
| 763 |
+
"grad_norm": 4.396152019500732,
|
| 764 |
+
"learning_rate": 5.1135555555555556e-05,
|
| 765 |
+
"loss": 1.5966,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 35.92617007251154,
|
| 770 |
+
"grad_norm": 4.942046165466309,
|
| 771 |
+
"learning_rate": 5.058000000000001e-05,
|
| 772 |
+
"loss": 1.591,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 36.255767963085034,
|
| 777 |
+
"grad_norm": 4.5848846435546875,
|
| 778 |
+
"learning_rate": 5.002444444444445e-05,
|
| 779 |
+
"loss": 1.5758,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 36.58536585365854,
|
| 784 |
+
"grad_norm": 5.14020299911499,
|
| 785 |
+
"learning_rate": 4.9468888888888894e-05,
|
| 786 |
+
"loss": 1.578,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 36.91496374423204,
|
| 791 |
+
"grad_norm": 3.547346353530884,
|
| 792 |
+
"learning_rate": 4.891333333333333e-05,
|
| 793 |
+
"loss": 1.5778,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 37.244561634805535,
|
| 798 |
+
"grad_norm": 4.23244047164917,
|
| 799 |
+
"learning_rate": 4.835888888888889e-05,
|
| 800 |
+
"loss": 1.5584,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 37.57415952537904,
|
| 805 |
+
"grad_norm": 4.20224666595459,
|
| 806 |
+
"learning_rate": 4.780333333333333e-05,
|
| 807 |
+
"loss": 1.5564,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 37.90375741595254,
|
| 812 |
+
"grad_norm": 5.5531229972839355,
|
| 813 |
+
"learning_rate": 4.724777777777778e-05,
|
| 814 |
+
"loss": 1.5509,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 38.233355306526036,
|
| 819 |
+
"grad_norm": 4.247383117675781,
|
| 820 |
+
"learning_rate": 4.6692222222222224e-05,
|
| 821 |
+
"loss": 1.5491,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 38.56295319709954,
|
| 826 |
+
"grad_norm": 4.918506622314453,
|
| 827 |
+
"learning_rate": 4.613777777777778e-05,
|
| 828 |
+
"loss": 1.5382,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 38.89255108767304,
|
| 833 |
+
"grad_norm": 5.86004114151001,
|
| 834 |
+
"learning_rate": 4.558222222222222e-05,
|
| 835 |
+
"loss": 1.5389,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 39.22214897824654,
|
| 840 |
+
"grad_norm": 4.52742862701416,
|
| 841 |
+
"learning_rate": 4.502666666666667e-05,
|
| 842 |
+
"loss": 1.5182,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 39.55174686882004,
|
| 847 |
+
"grad_norm": 4.052803993225098,
|
| 848 |
+
"learning_rate": 4.447111111111111e-05,
|
| 849 |
+
"loss": 1.5221,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 39.88134475939354,
|
| 854 |
+
"grad_norm": 4.366000175476074,
|
| 855 |
+
"learning_rate": 4.391555555555556e-05,
|
| 856 |
+
"loss": 1.5295,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 40.21094264996704,
|
| 861 |
+
"grad_norm": 3.8542122840881348,
|
| 862 |
+
"learning_rate": 4.3361111111111116e-05,
|
| 863 |
+
"loss": 1.5058,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 40.54054054054054,
|
| 868 |
+
"grad_norm": 5.032189846038818,
|
| 869 |
+
"learning_rate": 4.280555555555556e-05,
|
| 870 |
+
"loss": 1.5062,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 40.87013843111404,
|
| 875 |
+
"grad_norm": 5.24393367767334,
|
| 876 |
+
"learning_rate": 4.2250000000000004e-05,
|
| 877 |
+
"loss": 1.4969,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 41.19973632168754,
|
| 882 |
+
"grad_norm": 4.890485763549805,
|
| 883 |
+
"learning_rate": 4.169444444444445e-05,
|
| 884 |
+
"loss": 1.4985,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 41.52933421226104,
|
| 889 |
+
"grad_norm": 4.6505560874938965,
|
| 890 |
+
"learning_rate": 4.114e-05,
|
| 891 |
+
"loss": 1.4804,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 41.858932102834544,
|
| 896 |
+
"grad_norm": 4.209589958190918,
|
| 897 |
+
"learning_rate": 4.0584444444444446e-05,
|
| 898 |
+
"loss": 1.4786,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 42.18852999340804,
|
| 903 |
+
"grad_norm": 4.189364433288574,
|
| 904 |
+
"learning_rate": 4.00288888888889e-05,
|
| 905 |
+
"loss": 1.4822,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 42.51812788398154,
|
| 910 |
+
"grad_norm": 3.8995819091796875,
|
| 911 |
+
"learning_rate": 3.9473333333333334e-05,
|
| 912 |
+
"loss": 1.4585,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 42.847725774555045,
|
| 917 |
+
"grad_norm": 4.900391101837158,
|
| 918 |
+
"learning_rate": 3.891777777777778e-05,
|
| 919 |
+
"loss": 1.4711,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 43.17732366512854,
|
| 924 |
+
"grad_norm": 5.116580486297607,
|
| 925 |
+
"learning_rate": 3.836333333333333e-05,
|
| 926 |
+
"loss": 1.46,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 43.50692155570204,
|
| 931 |
+
"grad_norm": 4.404346466064453,
|
| 932 |
+
"learning_rate": 3.780777777777778e-05,
|
| 933 |
+
"loss": 1.4605,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 43.836519446275545,
|
| 938 |
+
"grad_norm": 4.413264274597168,
|
| 939 |
+
"learning_rate": 3.725222222222222e-05,
|
| 940 |
+
"loss": 1.4555,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 44.16611733684904,
|
| 945 |
+
"grad_norm": 4.489921569824219,
|
| 946 |
+
"learning_rate": 3.669666666666667e-05,
|
| 947 |
+
"loss": 1.4455,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 44.495715227422544,
|
| 952 |
+
"grad_norm": 5.347376346588135,
|
| 953 |
+
"learning_rate": 3.6141111111111114e-05,
|
| 954 |
+
"loss": 1.4284,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 44.825313117996046,
|
| 959 |
+
"grad_norm": 5.003966808319092,
|
| 960 |
+
"learning_rate": 3.558555555555556e-05,
|
| 961 |
+
"loss": 1.4409,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 45.15491100856954,
|
| 966 |
+
"grad_norm": 4.405020713806152,
|
| 967 |
+
"learning_rate": 3.503e-05,
|
| 968 |
+
"loss": 1.4407,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 45.484508899143044,
|
| 973 |
+
"grad_norm": 5.011410236358643,
|
| 974 |
+
"learning_rate": 3.447555555555556e-05,
|
| 975 |
+
"loss": 1.4267,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 45.81410678971655,
|
| 980 |
+
"grad_norm": 4.72757625579834,
|
| 981 |
+
"learning_rate": 3.392e-05,
|
| 982 |
+
"loss": 1.4186,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 46.14370468029005,
|
| 987 |
+
"grad_norm": 5.578848838806152,
|
| 988 |
+
"learning_rate": 3.336444444444445e-05,
|
| 989 |
+
"loss": 1.4178,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 46.473302570863545,
|
| 994 |
+
"grad_norm": 5.183284282684326,
|
| 995 |
+
"learning_rate": 3.280888888888889e-05,
|
| 996 |
+
"loss": 1.3985,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 46.80290046143705,
|
| 1001 |
+
"grad_norm": 4.183593273162842,
|
| 1002 |
+
"learning_rate": 3.225333333333334e-05,
|
| 1003 |
+
"loss": 1.4083,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 47.13249835201055,
|
| 1008 |
+
"grad_norm": 5.600123405456543,
|
| 1009 |
+
"learning_rate": 3.169888888888889e-05,
|
| 1010 |
+
"loss": 1.4003,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 47.462096242584046,
|
| 1015 |
+
"grad_norm": 4.25091552734375,
|
| 1016 |
+
"learning_rate": 3.114333333333334e-05,
|
| 1017 |
+
"loss": 1.3864,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 47.79169413315755,
|
| 1022 |
+
"grad_norm": 4.143881797790527,
|
| 1023 |
+
"learning_rate": 3.058777777777778e-05,
|
| 1024 |
+
"loss": 1.3949,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 48.12129202373105,
|
| 1029 |
+
"grad_norm": 4.745497226715088,
|
| 1030 |
+
"learning_rate": 3.003222222222222e-05,
|
| 1031 |
+
"loss": 1.3879,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 48.45088991430455,
|
| 1036 |
+
"grad_norm": 4.981921195983887,
|
| 1037 |
+
"learning_rate": 2.9477777777777783e-05,
|
| 1038 |
+
"loss": 1.3815,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 48.78048780487805,
|
| 1043 |
+
"grad_norm": 5.088881969451904,
|
| 1044 |
+
"learning_rate": 2.8922222222222224e-05,
|
| 1045 |
+
"loss": 1.3826,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 49.11008569545155,
|
| 1050 |
+
"grad_norm": 5.574970722198486,
|
| 1051 |
+
"learning_rate": 2.836666666666667e-05,
|
| 1052 |
+
"loss": 1.3739,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 49.43968358602505,
|
| 1057 |
+
"grad_norm": 4.544190406799316,
|
| 1058 |
+
"learning_rate": 2.781111111111111e-05,
|
| 1059 |
+
"loss": 1.362,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 49.76928147659855,
|
| 1064 |
+
"grad_norm": 6.205341339111328,
|
| 1065 |
+
"learning_rate": 2.7255555555555555e-05,
|
| 1066 |
+
"loss": 1.3758,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 50.09887936717205,
|
| 1071 |
+
"grad_norm": 4.284372806549072,
|
| 1072 |
+
"learning_rate": 2.670111111111111e-05,
|
| 1073 |
+
"loss": 1.3579,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 50.42847725774555,
|
| 1078 |
+
"grad_norm": 4.453866481781006,
|
| 1079 |
+
"learning_rate": 2.6145555555555557e-05,
|
| 1080 |
+
"loss": 1.3456,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 50.75807514831905,
|
| 1085 |
+
"grad_norm": 5.443893909454346,
|
| 1086 |
+
"learning_rate": 2.5590000000000004e-05,
|
| 1087 |
+
"loss": 1.3458,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 51.087673038892554,
|
| 1092 |
+
"grad_norm": 5.104333877563477,
|
| 1093 |
+
"learning_rate": 2.5034444444444444e-05,
|
| 1094 |
+
"loss": 1.3416,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 51.41727092946605,
|
| 1099 |
+
"grad_norm": 5.528281211853027,
|
| 1100 |
+
"learning_rate": 2.447888888888889e-05,
|
| 1101 |
+
"loss": 1.3368,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 51.74686882003955,
|
| 1106 |
+
"grad_norm": 4.898233413696289,
|
| 1107 |
+
"learning_rate": 2.3923333333333335e-05,
|
| 1108 |
+
"loss": 1.3421,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 52.076466710613055,
|
| 1113 |
+
"grad_norm": 5.019732475280762,
|
| 1114 |
+
"learning_rate": 2.336777777777778e-05,
|
| 1115 |
+
"loss": 1.3317,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 52.40606460118655,
|
| 1120 |
+
"grad_norm": 4.299033164978027,
|
| 1121 |
+
"learning_rate": 2.2812222222222223e-05,
|
| 1122 |
+
"loss": 1.3227,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 52.73566249176005,
|
| 1127 |
+
"grad_norm": 4.310223579406738,
|
| 1128 |
+
"learning_rate": 2.225777777777778e-05,
|
| 1129 |
+
"loss": 1.3147,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 53.065260382333555,
|
| 1134 |
+
"grad_norm": 3.8718271255493164,
|
| 1135 |
+
"learning_rate": 2.1702222222222225e-05,
|
| 1136 |
+
"loss": 1.3322,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 53.39485827290705,
|
| 1141 |
+
"grad_norm": 4.97250509262085,
|
| 1142 |
+
"learning_rate": 2.114666666666667e-05,
|
| 1143 |
+
"loss": 1.3307,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 53.72445616348055,
|
| 1148 |
+
"grad_norm": 4.575880527496338,
|
| 1149 |
+
"learning_rate": 2.0591111111111112e-05,
|
| 1150 |
+
"loss": 1.3084,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 54.054054054054056,
|
| 1155 |
+
"grad_norm": 4.751391887664795,
|
| 1156 |
+
"learning_rate": 2.0036666666666667e-05,
|
| 1157 |
+
"loss": 1.3137,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 54.38365194462755,
|
| 1162 |
+
"grad_norm": 5.039731502532959,
|
| 1163 |
+
"learning_rate": 1.948111111111111e-05,
|
| 1164 |
+
"loss": 1.3013,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 54.713249835201054,
|
| 1169 |
+
"grad_norm": 5.60392427444458,
|
| 1170 |
+
"learning_rate": 1.8925555555555558e-05,
|
| 1171 |
+
"loss": 1.3038,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 55.04284772577456,
|
| 1176 |
+
"grad_norm": 5.029587745666504,
|
| 1177 |
+
"learning_rate": 1.8370000000000002e-05,
|
| 1178 |
+
"loss": 1.303,
|
| 1179 |
+
"step": 83500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 55.37244561634805,
|
| 1183 |
+
"grad_norm": 5.2431559562683105,
|
| 1184 |
+
"learning_rate": 1.7815555555555557e-05,
|
| 1185 |
+
"loss": 1.2928,
|
| 1186 |
+
"step": 84000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 55.702043506921555,
|
| 1190 |
+
"grad_norm": 4.04716682434082,
|
| 1191 |
+
"learning_rate": 1.726e-05,
|
| 1192 |
+
"loss": 1.2923,
|
| 1193 |
+
"step": 84500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 56.03164139749506,
|
| 1197 |
+
"grad_norm": 4.244519233703613,
|
| 1198 |
+
"learning_rate": 1.6704444444444445e-05,
|
| 1199 |
+
"loss": 1.2979,
|
| 1200 |
+
"step": 85000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 56.36123928806855,
|
| 1204 |
+
"grad_norm": 4.713144779205322,
|
| 1205 |
+
"learning_rate": 1.6148888888888888e-05,
|
| 1206 |
+
"loss": 1.274,
|
| 1207 |
+
"step": 85500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 56.690837178642056,
|
| 1211 |
+
"grad_norm": 4.156798362731934,
|
| 1212 |
+
"learning_rate": 1.5594444444444443e-05,
|
| 1213 |
+
"loss": 1.2837,
|
| 1214 |
+
"step": 86000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 57.02043506921556,
|
| 1218 |
+
"grad_norm": 3.8550474643707275,
|
| 1219 |
+
"learning_rate": 1.5038888888888889e-05,
|
| 1220 |
+
"loss": 1.2883,
|
| 1221 |
+
"step": 86500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 57.350032959789054,
|
| 1225 |
+
"grad_norm": 5.007939338684082,
|
| 1226 |
+
"learning_rate": 1.4483333333333334e-05,
|
| 1227 |
+
"loss": 1.2914,
|
| 1228 |
+
"step": 87000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 57.67963085036256,
|
| 1232 |
+
"grad_norm": 4.951704502105713,
|
| 1233 |
+
"learning_rate": 1.3927777777777778e-05,
|
| 1234 |
+
"loss": 1.2676,
|
| 1235 |
+
"step": 87500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 58.00922874093606,
|
| 1239 |
+
"grad_norm": 4.468066215515137,
|
| 1240 |
+
"learning_rate": 1.3373333333333335e-05,
|
| 1241 |
+
"loss": 1.2715,
|
| 1242 |
+
"step": 88000
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 58.338826631509555,
|
| 1246 |
+
"grad_norm": 4.884173393249512,
|
| 1247 |
+
"learning_rate": 1.2817777777777778e-05,
|
| 1248 |
+
"loss": 1.258,
|
| 1249 |
+
"step": 88500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 58.66842452208306,
|
| 1253 |
+
"grad_norm": 4.791373252868652,
|
| 1254 |
+
"learning_rate": 1.2262222222222222e-05,
|
| 1255 |
+
"loss": 1.2769,
|
| 1256 |
+
"step": 89000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 58.99802241265656,
|
| 1260 |
+
"grad_norm": 4.951115608215332,
|
| 1261 |
+
"learning_rate": 1.1706666666666668e-05,
|
| 1262 |
+
"loss": 1.2632,
|
| 1263 |
+
"step": 89500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 59.32762030323006,
|
| 1267 |
+
"grad_norm": 5.155387878417969,
|
| 1268 |
+
"learning_rate": 1.1152222222222223e-05,
|
| 1269 |
+
"loss": 1.251,
|
| 1270 |
+
"step": 90000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 59.65721819380356,
|
| 1274 |
+
"grad_norm": 4.434185981750488,
|
| 1275 |
+
"learning_rate": 1.0596666666666668e-05,
|
| 1276 |
+
"loss": 1.2639,
|
| 1277 |
+
"step": 90500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 59.98681608437706,
|
| 1281 |
+
"grad_norm": 4.74413537979126,
|
| 1282 |
+
"learning_rate": 1.0041111111111112e-05,
|
| 1283 |
+
"loss": 1.2559,
|
| 1284 |
+
"step": 91000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 60.316413974950564,
|
| 1288 |
+
"grad_norm": 5.1248579025268555,
|
| 1289 |
+
"learning_rate": 9.485555555555555e-06,
|
| 1290 |
+
"loss": 1.2477,
|
| 1291 |
+
"step": 91500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 60.64601186552406,
|
| 1295 |
+
"grad_norm": 4.244519233703613,
|
| 1296 |
+
"learning_rate": 8.930000000000001e-06,
|
| 1297 |
+
"loss": 1.2467,
|
| 1298 |
+
"step": 92000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 60.97560975609756,
|
| 1302 |
+
"grad_norm": 4.941471576690674,
|
| 1303 |
+
"learning_rate": 8.374444444444445e-06,
|
| 1304 |
+
"loss": 1.253,
|
| 1305 |
+
"step": 92500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 61.305207646671064,
|
| 1309 |
+
"grad_norm": 4.738947868347168,
|
| 1310 |
+
"learning_rate": 7.820000000000001e-06,
|
| 1311 |
+
"loss": 1.2395,
|
| 1312 |
+
"step": 93000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 61.63480553724456,
|
| 1316 |
+
"grad_norm": 4.912777900695801,
|
| 1317 |
+
"learning_rate": 7.264444444444444e-06,
|
| 1318 |
+
"loss": 1.2435,
|
| 1319 |
+
"step": 93500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 61.96440342781806,
|
| 1323 |
+
"grad_norm": 4.210970401763916,
|
| 1324 |
+
"learning_rate": 6.70888888888889e-06,
|
| 1325 |
+
"loss": 1.2427,
|
| 1326 |
+
"step": 94000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 62.294001318391565,
|
| 1330 |
+
"grad_norm": 4.806487083435059,
|
| 1331 |
+
"learning_rate": 6.153333333333334e-06,
|
| 1332 |
+
"loss": 1.2409,
|
| 1333 |
+
"step": 94500
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 62.62359920896506,
|
| 1337 |
+
"grad_norm": 4.413333415985107,
|
| 1338 |
+
"learning_rate": 5.597777777777778e-06,
|
| 1339 |
+
"loss": 1.2268,
|
| 1340 |
+
"step": 95000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 62.95319709953856,
|
| 1344 |
+
"grad_norm": 4.221549034118652,
|
| 1345 |
+
"learning_rate": 5.042222222222223e-06,
|
| 1346 |
+
"loss": 1.2333,
|
| 1347 |
+
"step": 95500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 63.282794990112066,
|
| 1351 |
+
"grad_norm": 6.8003106117248535,
|
| 1352 |
+
"learning_rate": 4.486666666666667e-06,
|
| 1353 |
+
"loss": 1.2314,
|
| 1354 |
+
"step": 96000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 63.61239288068556,
|
| 1358 |
+
"grad_norm": 4.016542434692383,
|
| 1359 |
+
"learning_rate": 3.931111111111111e-06,
|
| 1360 |
+
"loss": 1.2315,
|
| 1361 |
+
"step": 96500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 63.941990771259064,
|
| 1365 |
+
"grad_norm": 4.306130409240723,
|
| 1366 |
+
"learning_rate": 3.3777777777777777e-06,
|
| 1367 |
+
"loss": 1.2212,
|
| 1368 |
+
"step": 97000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 64.27158866183257,
|
| 1372 |
+
"grad_norm": 5.162050724029541,
|
| 1373 |
+
"learning_rate": 2.8222222222222223e-06,
|
| 1374 |
+
"loss": 1.2209,
|
| 1375 |
+
"step": 97500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 64.60118655240606,
|
| 1379 |
+
"grad_norm": 5.353754043579102,
|
| 1380 |
+
"learning_rate": 2.266666666666667e-06,
|
| 1381 |
+
"loss": 1.234,
|
| 1382 |
+
"step": 98000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 64.93078444297956,
|
| 1386 |
+
"grad_norm": 5.8871588706970215,
|
| 1387 |
+
"learning_rate": 1.7111111111111112e-06,
|
| 1388 |
+
"loss": 1.2348,
|
| 1389 |
+
"step": 98500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 65.26038233355307,
|
| 1393 |
+
"grad_norm": 4.3622307777404785,
|
| 1394 |
+
"learning_rate": 1.1555555555555556e-06,
|
| 1395 |
+
"loss": 1.2248,
|
| 1396 |
+
"step": 99000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 65.58998022412656,
|
| 1400 |
+
"grad_norm": 6.211566925048828,
|
| 1401 |
+
"learning_rate": 6.000000000000001e-07,
|
| 1402 |
+
"loss": 1.2248,
|
| 1403 |
+
"step": 99500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 65.91957811470007,
|
| 1407 |
+
"grad_norm": 4.36595344543457,
|
| 1408 |
+
"learning_rate": 4.444444444444445e-08,
|
| 1409 |
+
"loss": 1.2218,
|
| 1410 |
+
"step": 100000
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 500,
|
| 1414 |
+
"max_steps": 100000,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 66,
|
| 1417 |
+
"save_steps": 20000,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": true
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 3.162161010232074e+17,
|
| 1431 |
+
"train_batch_size": 32,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69df6ad8c68fb54108512e3e72f6cf8c86833f012b145d178a64ad70f75abaa
|
| 3 |
+
size 5368
|
checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20000/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": 514,
|
| 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": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-20000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a28f777dc403e9ae8257784714064b19cf6b24937e442ad1036ca5338065188
|
| 3 |
+
size 334030264
|
checkpoint-20000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa60e3811f148d7c6e33f6ebc7e13c9d829b25cebc87f43f3fea38213691bdb
|
| 3 |
+
size 668124218
|
checkpoint-20000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4107d32222195fda0f34af96f8ceb3e0aab1747bdae077e0e491a2be8c090dfd
|
| 3 |
+
size 14244
|
checkpoint-20000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0a063eb0473b3b545a1a6d08a6917737011cdcb54e4175440233b96c566f83c
|
| 3 |
+
size 988
|
checkpoint-20000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def1f8e757eaba62de49803df826dc640ae480089776545ee91df066dd21ca94
|
| 3 |
+
size 1064
|
checkpoint-20000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-20000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-20000/trainer_state.json
ADDED
|
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.183915622940013,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 20000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3295978905735003,
|
| 14 |
+
"grad_norm": 2.8918700218200684,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.1735,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6591957811470006,
|
| 21 |
+
"grad_norm": 2.0813119411468506,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 8.4577,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.988793671720501,
|
| 28 |
+
"grad_norm": 1.871568202972412,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 7.6313,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.3183915622940012,
|
| 35 |
+
"grad_norm": 1.7127728462219238,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 7.3405,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.6479894528675016,
|
| 42 |
+
"grad_norm": 1.7611004114151,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 7.1579,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.977587343441002,
|
| 49 |
+
"grad_norm": 1.7559301853179932,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 7.0353,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.3071852340145025,
|
| 56 |
+
"grad_norm": 2.062741994857788,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 6.949,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.6367831245880025,
|
| 63 |
+
"grad_norm": 2.037240505218506,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 6.8905,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.966381015161503,
|
| 70 |
+
"grad_norm": 2.732247829437256,
|
| 71 |
+
"learning_rate": 4.5e-05,
|
| 72 |
+
"loss": 6.8433,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.2959789057350033,
|
| 77 |
+
"grad_norm": 2.648927927017212,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 6.7753,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.6255767963085037,
|
| 84 |
+
"grad_norm": 3.1528918743133545,
|
| 85 |
+
"learning_rate": 5.500000000000001e-05,
|
| 86 |
+
"loss": 6.747,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.955174686882004,
|
| 91 |
+
"grad_norm": 2.9101691246032715,
|
| 92 |
+
"learning_rate": 6e-05,
|
| 93 |
+
"loss": 6.7081,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.284772577455504,
|
| 98 |
+
"grad_norm": 2.407719612121582,
|
| 99 |
+
"learning_rate": 6.499000000000001e-05,
|
| 100 |
+
"loss": 6.6724,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.614370468029005,
|
| 105 |
+
"grad_norm": 1.8148102760314941,
|
| 106 |
+
"learning_rate": 6.999e-05,
|
| 107 |
+
"loss": 6.6584,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.943968358602505,
|
| 112 |
+
"grad_norm": 2.6724727153778076,
|
| 113 |
+
"learning_rate": 7.499e-05,
|
| 114 |
+
"loss": 6.6439,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.273566249176005,
|
| 119 |
+
"grad_norm": 2.199885368347168,
|
| 120 |
+
"learning_rate": 7.999000000000001e-05,
|
| 121 |
+
"loss": 6.592,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.603164139749506,
|
| 126 |
+
"grad_norm": 2.2242558002471924,
|
| 127 |
+
"learning_rate": 8.498e-05,
|
| 128 |
+
"loss": 6.5687,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.932762030323006,
|
| 133 |
+
"grad_norm": 3.0547144412994385,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 6.5339,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.262359920896507,
|
| 140 |
+
"grad_norm": 3.8027408123016357,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 6.4818,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.591957811470007,
|
| 147 |
+
"grad_norm": 2.3049635887145996,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 6.392,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.921555702043507,
|
| 154 |
+
"grad_norm": 3.5188333988189697,
|
| 155 |
+
"learning_rate": 9.944777777777778e-05,
|
| 156 |
+
"loss": 6.2095,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.251153592617007,
|
| 161 |
+
"grad_norm": 5.0908050537109375,
|
| 162 |
+
"learning_rate": 9.889222222222223e-05,
|
| 163 |
+
"loss": 5.8004,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.580751483190507,
|
| 168 |
+
"grad_norm": 4.9945068359375,
|
| 169 |
+
"learning_rate": 9.833777777777779e-05,
|
| 170 |
+
"loss": 5.3376,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.910349373764008,
|
| 175 |
+
"grad_norm": 4.765307426452637,
|
| 176 |
+
"learning_rate": 9.778222222222222e-05,
|
| 177 |
+
"loss": 4.9592,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 8.23994726433751,
|
| 182 |
+
"grad_norm": 4.015578269958496,
|
| 183 |
+
"learning_rate": 9.722666666666666e-05,
|
| 184 |
+
"loss": 4.5913,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.569545154911008,
|
| 189 |
+
"grad_norm": 4.644675254821777,
|
| 190 |
+
"learning_rate": 9.667111111111111e-05,
|
| 191 |
+
"loss": 4.3206,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.899143045484509,
|
| 196 |
+
"grad_norm": 3.8366589546203613,
|
| 197 |
+
"learning_rate": 9.611555555555556e-05,
|
| 198 |
+
"loss": 4.1122,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 9.22874093605801,
|
| 203 |
+
"grad_norm": 4.115426540374756,
|
| 204 |
+
"learning_rate": 9.556111111111112e-05,
|
| 205 |
+
"loss": 3.8972,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.558338826631509,
|
| 210 |
+
"grad_norm": 4.137101650238037,
|
| 211 |
+
"learning_rate": 9.500555555555555e-05,
|
| 212 |
+
"loss": 3.7381,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.88793671720501,
|
| 217 |
+
"grad_norm": 5.157057285308838,
|
| 218 |
+
"learning_rate": 9.445e-05,
|
| 219 |
+
"loss": 3.6142,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 10.21753460777851,
|
| 224 |
+
"grad_norm": 3.9190354347229004,
|
| 225 |
+
"learning_rate": 9.389444444444446e-05,
|
| 226 |
+
"loss": 3.4768,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.54713249835201,
|
| 231 |
+
"grad_norm": 3.799747943878174,
|
| 232 |
+
"learning_rate": 9.333888888888889e-05,
|
| 233 |
+
"loss": 3.3694,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.87673038892551,
|
| 238 |
+
"grad_norm": 4.951575756072998,
|
| 239 |
+
"learning_rate": 9.278333333333333e-05,
|
| 240 |
+
"loss": 3.2834,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 11.206328279499012,
|
| 245 |
+
"grad_norm": 3.807826042175293,
|
| 246 |
+
"learning_rate": 9.222777777777778e-05,
|
| 247 |
+
"loss": 3.176,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.53592617007251,
|
| 252 |
+
"grad_norm": 4.53897762298584,
|
| 253 |
+
"learning_rate": 9.167222222222223e-05,
|
| 254 |
+
"loss": 3.096,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.865524060646012,
|
| 259 |
+
"grad_norm": 4.1547980308532715,
|
| 260 |
+
"learning_rate": 9.111777777777779e-05,
|
| 261 |
+
"loss": 3.0208,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 12.195121951219512,
|
| 266 |
+
"grad_norm": 4.5414719581604,
|
| 267 |
+
"learning_rate": 9.056222222222222e-05,
|
| 268 |
+
"loss": 2.9412,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.524719841793013,
|
| 273 |
+
"grad_norm": 4.638998508453369,
|
| 274 |
+
"learning_rate": 9.000666666666667e-05,
|
| 275 |
+
"loss": 2.8768,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.854317732366512,
|
| 280 |
+
"grad_norm": 3.492238759994507,
|
| 281 |
+
"learning_rate": 8.945111111111112e-05,
|
| 282 |
+
"loss": 2.8319,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 13.183915622940013,
|
| 287 |
+
"grad_norm": 3.963812828063965,
|
| 288 |
+
"learning_rate": 8.889666666666668e-05,
|
| 289 |
+
"loss": 2.7481,
|
| 290 |
+
"step": 20000
|
| 291 |
+
}
|
| 292 |
+
],
|
| 293 |
+
"logging_steps": 500,
|
| 294 |
+
"max_steps": 100000,
|
| 295 |
+
"num_input_tokens_seen": 0,
|
| 296 |
+
"num_train_epochs": 66,
|
| 297 |
+
"save_steps": 20000,
|
| 298 |
+
"stateful_callbacks": {
|
| 299 |
+
"TrainerControl": {
|
| 300 |
+
"args": {
|
| 301 |
+
"should_epoch_stop": false,
|
| 302 |
+
"should_evaluate": false,
|
| 303 |
+
"should_log": false,
|
| 304 |
+
"should_save": true,
|
| 305 |
+
"should_training_stop": false
|
| 306 |
+
},
|
| 307 |
+
"attributes": {}
|
| 308 |
+
}
|
| 309 |
+
},
|
| 310 |
+
"total_flos": 6.320860120633344e+16,
|
| 311 |
+
"train_batch_size": 32,
|
| 312 |
+
"trial_name": null,
|
| 313 |
+
"trial_params": null
|
| 314 |
+
}
|
checkpoint-20000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69df6ad8c68fb54108512e3e72f6cf8c86833f012b145d178a64ad70f75abaa
|
| 3 |
+
size 5368
|
checkpoint-20000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-40000/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": 514,
|
| 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": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51be73365e3cc766212ecf6fcdd92d3b8e19bf67fecdf60e13cf82781180f28e
|
| 3 |
+
size 334030264
|
checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1275898c1b8374435f94a24fc5cbb8db9a06df1503e12b35f8bc01ebae1472c8
|
| 3 |
+
size 668124218
|
checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00e6992831490356db068056b5afcafbd66479643aaf2d4cded3ad5a2065432d
|
| 3 |
+
size 14244
|
checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33e042e7b6a5dfcc4fc5dfc513783322f11ca842c9b6104e6aa0bc0d1e4e03f6
|
| 3 |
+
size 988
|
checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e34b4cc09f761654c942ec9d190819f85a8aff20b3823a90e1900f44a11b9c
|
| 3 |
+
size 1064
|
checkpoint-40000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-40000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-40000/trainer_state.json
ADDED
|
@@ -0,0 +1,594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.367831245880026,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 40000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3295978905735003,
|
| 14 |
+
"grad_norm": 2.8918700218200684,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.1735,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6591957811470006,
|
| 21 |
+
"grad_norm": 2.0813119411468506,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 8.4577,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.988793671720501,
|
| 28 |
+
"grad_norm": 1.871568202972412,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 7.6313,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.3183915622940012,
|
| 35 |
+
"grad_norm": 1.7127728462219238,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 7.3405,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.6479894528675016,
|
| 42 |
+
"grad_norm": 1.7611004114151,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 7.1579,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.977587343441002,
|
| 49 |
+
"grad_norm": 1.7559301853179932,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 7.0353,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.3071852340145025,
|
| 56 |
+
"grad_norm": 2.062741994857788,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 6.949,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.6367831245880025,
|
| 63 |
+
"grad_norm": 2.037240505218506,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 6.8905,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.966381015161503,
|
| 70 |
+
"grad_norm": 2.732247829437256,
|
| 71 |
+
"learning_rate": 4.5e-05,
|
| 72 |
+
"loss": 6.8433,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.2959789057350033,
|
| 77 |
+
"grad_norm": 2.648927927017212,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 6.7753,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.6255767963085037,
|
| 84 |
+
"grad_norm": 3.1528918743133545,
|
| 85 |
+
"learning_rate": 5.500000000000001e-05,
|
| 86 |
+
"loss": 6.747,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.955174686882004,
|
| 91 |
+
"grad_norm": 2.9101691246032715,
|
| 92 |
+
"learning_rate": 6e-05,
|
| 93 |
+
"loss": 6.7081,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.284772577455504,
|
| 98 |
+
"grad_norm": 2.407719612121582,
|
| 99 |
+
"learning_rate": 6.499000000000001e-05,
|
| 100 |
+
"loss": 6.6724,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.614370468029005,
|
| 105 |
+
"grad_norm": 1.8148102760314941,
|
| 106 |
+
"learning_rate": 6.999e-05,
|
| 107 |
+
"loss": 6.6584,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.943968358602505,
|
| 112 |
+
"grad_norm": 2.6724727153778076,
|
| 113 |
+
"learning_rate": 7.499e-05,
|
| 114 |
+
"loss": 6.6439,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.273566249176005,
|
| 119 |
+
"grad_norm": 2.199885368347168,
|
| 120 |
+
"learning_rate": 7.999000000000001e-05,
|
| 121 |
+
"loss": 6.592,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.603164139749506,
|
| 126 |
+
"grad_norm": 2.2242558002471924,
|
| 127 |
+
"learning_rate": 8.498e-05,
|
| 128 |
+
"loss": 6.5687,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.932762030323006,
|
| 133 |
+
"grad_norm": 3.0547144412994385,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 6.5339,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.262359920896507,
|
| 140 |
+
"grad_norm": 3.8027408123016357,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 6.4818,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.591957811470007,
|
| 147 |
+
"grad_norm": 2.3049635887145996,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 6.392,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.921555702043507,
|
| 154 |
+
"grad_norm": 3.5188333988189697,
|
| 155 |
+
"learning_rate": 9.944777777777778e-05,
|
| 156 |
+
"loss": 6.2095,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.251153592617007,
|
| 161 |
+
"grad_norm": 5.0908050537109375,
|
| 162 |
+
"learning_rate": 9.889222222222223e-05,
|
| 163 |
+
"loss": 5.8004,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.580751483190507,
|
| 168 |
+
"grad_norm": 4.9945068359375,
|
| 169 |
+
"learning_rate": 9.833777777777779e-05,
|
| 170 |
+
"loss": 5.3376,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.910349373764008,
|
| 175 |
+
"grad_norm": 4.765307426452637,
|
| 176 |
+
"learning_rate": 9.778222222222222e-05,
|
| 177 |
+
"loss": 4.9592,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 8.23994726433751,
|
| 182 |
+
"grad_norm": 4.015578269958496,
|
| 183 |
+
"learning_rate": 9.722666666666666e-05,
|
| 184 |
+
"loss": 4.5913,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.569545154911008,
|
| 189 |
+
"grad_norm": 4.644675254821777,
|
| 190 |
+
"learning_rate": 9.667111111111111e-05,
|
| 191 |
+
"loss": 4.3206,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.899143045484509,
|
| 196 |
+
"grad_norm": 3.8366589546203613,
|
| 197 |
+
"learning_rate": 9.611555555555556e-05,
|
| 198 |
+
"loss": 4.1122,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 9.22874093605801,
|
| 203 |
+
"grad_norm": 4.115426540374756,
|
| 204 |
+
"learning_rate": 9.556111111111112e-05,
|
| 205 |
+
"loss": 3.8972,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.558338826631509,
|
| 210 |
+
"grad_norm": 4.137101650238037,
|
| 211 |
+
"learning_rate": 9.500555555555555e-05,
|
| 212 |
+
"loss": 3.7381,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.88793671720501,
|
| 217 |
+
"grad_norm": 5.157057285308838,
|
| 218 |
+
"learning_rate": 9.445e-05,
|
| 219 |
+
"loss": 3.6142,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 10.21753460777851,
|
| 224 |
+
"grad_norm": 3.9190354347229004,
|
| 225 |
+
"learning_rate": 9.389444444444446e-05,
|
| 226 |
+
"loss": 3.4768,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.54713249835201,
|
| 231 |
+
"grad_norm": 3.799747943878174,
|
| 232 |
+
"learning_rate": 9.333888888888889e-05,
|
| 233 |
+
"loss": 3.3694,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.87673038892551,
|
| 238 |
+
"grad_norm": 4.951575756072998,
|
| 239 |
+
"learning_rate": 9.278333333333333e-05,
|
| 240 |
+
"loss": 3.2834,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 11.206328279499012,
|
| 245 |
+
"grad_norm": 3.807826042175293,
|
| 246 |
+
"learning_rate": 9.222777777777778e-05,
|
| 247 |
+
"loss": 3.176,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.53592617007251,
|
| 252 |
+
"grad_norm": 4.53897762298584,
|
| 253 |
+
"learning_rate": 9.167222222222223e-05,
|
| 254 |
+
"loss": 3.096,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.865524060646012,
|
| 259 |
+
"grad_norm": 4.1547980308532715,
|
| 260 |
+
"learning_rate": 9.111777777777779e-05,
|
| 261 |
+
"loss": 3.0208,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 12.195121951219512,
|
| 266 |
+
"grad_norm": 4.5414719581604,
|
| 267 |
+
"learning_rate": 9.056222222222222e-05,
|
| 268 |
+
"loss": 2.9412,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.524719841793013,
|
| 273 |
+
"grad_norm": 4.638998508453369,
|
| 274 |
+
"learning_rate": 9.000666666666667e-05,
|
| 275 |
+
"loss": 2.8768,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.854317732366512,
|
| 280 |
+
"grad_norm": 3.492238759994507,
|
| 281 |
+
"learning_rate": 8.945111111111112e-05,
|
| 282 |
+
"loss": 2.8319,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 13.183915622940013,
|
| 287 |
+
"grad_norm": 3.963812828063965,
|
| 288 |
+
"learning_rate": 8.889666666666668e-05,
|
| 289 |
+
"loss": 2.7481,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.513513513513514,
|
| 294 |
+
"grad_norm": 4.802724361419678,
|
| 295 |
+
"learning_rate": 8.834111111111112e-05,
|
| 296 |
+
"loss": 2.7044,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.843111404087013,
|
| 301 |
+
"grad_norm": 4.897942066192627,
|
| 302 |
+
"learning_rate": 8.778555555555555e-05,
|
| 303 |
+
"loss": 2.6523,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 14.172709294660514,
|
| 308 |
+
"grad_norm": 4.577375411987305,
|
| 309 |
+
"learning_rate": 8.723e-05,
|
| 310 |
+
"loss": 2.6131,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.502307185234015,
|
| 315 |
+
"grad_norm": 4.424295902252197,
|
| 316 |
+
"learning_rate": 8.667444444444444e-05,
|
| 317 |
+
"loss": 2.5573,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 14.831905075807516,
|
| 322 |
+
"grad_norm": 4.2922749519348145,
|
| 323 |
+
"learning_rate": 8.612e-05,
|
| 324 |
+
"loss": 2.5337,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 15.161502966381015,
|
| 329 |
+
"grad_norm": 4.366146564483643,
|
| 330 |
+
"learning_rate": 8.556444444444445e-05,
|
| 331 |
+
"loss": 2.4788,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.491100856954516,
|
| 336 |
+
"grad_norm": 4.874686241149902,
|
| 337 |
+
"learning_rate": 8.50088888888889e-05,
|
| 338 |
+
"loss": 2.4399,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.820698747528017,
|
| 343 |
+
"grad_norm": 5.1893463134765625,
|
| 344 |
+
"learning_rate": 8.445333333333333e-05,
|
| 345 |
+
"loss": 2.4304,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.150296638101516,
|
| 350 |
+
"grad_norm": 4.169196605682373,
|
| 351 |
+
"learning_rate": 8.389888888888889e-05,
|
| 352 |
+
"loss": 2.3779,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.47989452867502,
|
| 357 |
+
"grad_norm": 4.332625865936279,
|
| 358 |
+
"learning_rate": 8.334333333333334e-05,
|
| 359 |
+
"loss": 2.3538,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.809492419248517,
|
| 364 |
+
"grad_norm": 5.98911190032959,
|
| 365 |
+
"learning_rate": 8.278777777777779e-05,
|
| 366 |
+
"loss": 2.3304,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.139090309822016,
|
| 371 |
+
"grad_norm": 4.644032001495361,
|
| 372 |
+
"learning_rate": 8.223222222222223e-05,
|
| 373 |
+
"loss": 2.3024,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 17.46868820039552,
|
| 378 |
+
"grad_norm": 4.4497971534729,
|
| 379 |
+
"learning_rate": 8.167777777777778e-05,
|
| 380 |
+
"loss": 2.2653,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.798286090969018,
|
| 385 |
+
"grad_norm": 3.7030065059661865,
|
| 386 |
+
"learning_rate": 8.112222222222222e-05,
|
| 387 |
+
"loss": 2.2525,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 18.127883981542517,
|
| 392 |
+
"grad_norm": 4.448596000671387,
|
| 393 |
+
"learning_rate": 8.056777777777779e-05,
|
| 394 |
+
"loss": 2.2154,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 18.45748187211602,
|
| 399 |
+
"grad_norm": 4.464804649353027,
|
| 400 |
+
"learning_rate": 8.001222222222222e-05,
|
| 401 |
+
"loss": 2.2012,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.78707976268952,
|
| 406 |
+
"grad_norm": 4.686955451965332,
|
| 407 |
+
"learning_rate": 7.945666666666667e-05,
|
| 408 |
+
"loss": 2.1827,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 19.116677653263018,
|
| 413 |
+
"grad_norm": 3.8840394020080566,
|
| 414 |
+
"learning_rate": 7.890111111111111e-05,
|
| 415 |
+
"loss": 2.1409,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 19.44627554383652,
|
| 420 |
+
"grad_norm": 3.527129888534546,
|
| 421 |
+
"learning_rate": 7.834555555555556e-05,
|
| 422 |
+
"loss": 2.1215,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.77587343441002,
|
| 427 |
+
"grad_norm": 5.817971706390381,
|
| 428 |
+
"learning_rate": 7.779000000000001e-05,
|
| 429 |
+
"loss": 2.1161,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 20.10547132498352,
|
| 434 |
+
"grad_norm": 5.153094291687012,
|
| 435 |
+
"learning_rate": 7.723444444444444e-05,
|
| 436 |
+
"loss": 2.0967,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 20.43506921555702,
|
| 441 |
+
"grad_norm": 5.022122859954834,
|
| 442 |
+
"learning_rate": 7.667888888888889e-05,
|
| 443 |
+
"loss": 2.0789,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.76466710613052,
|
| 448 |
+
"grad_norm": 4.343278884887695,
|
| 449 |
+
"learning_rate": 7.612444444444444e-05,
|
| 450 |
+
"loss": 2.0725,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 21.09426499670402,
|
| 455 |
+
"grad_norm": 5.50627326965332,
|
| 456 |
+
"learning_rate": 7.556888888888889e-05,
|
| 457 |
+
"loss": 2.0538,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 21.423862887277522,
|
| 462 |
+
"grad_norm": 4.042550563812256,
|
| 463 |
+
"learning_rate": 7.501333333333333e-05,
|
| 464 |
+
"loss": 2.0334,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.75346077785102,
|
| 469 |
+
"grad_norm": 5.352642059326172,
|
| 470 |
+
"learning_rate": 7.445777777777778e-05,
|
| 471 |
+
"loss": 2.0204,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 22.08305866842452,
|
| 476 |
+
"grad_norm": 4.7281494140625,
|
| 477 |
+
"learning_rate": 7.390333333333333e-05,
|
| 478 |
+
"loss": 2.0143,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 22.412656558998023,
|
| 483 |
+
"grad_norm": 5.191075801849365,
|
| 484 |
+
"learning_rate": 7.334777777777778e-05,
|
| 485 |
+
"loss": 1.9848,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.742254449571522,
|
| 490 |
+
"grad_norm": 3.772347927093506,
|
| 491 |
+
"learning_rate": 7.279222222222222e-05,
|
| 492 |
+
"loss": 1.9792,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 23.071852340145025,
|
| 497 |
+
"grad_norm": 4.231102466583252,
|
| 498 |
+
"learning_rate": 7.223666666666667e-05,
|
| 499 |
+
"loss": 1.9795,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 23.401450230718524,
|
| 504 |
+
"grad_norm": 4.547638416290283,
|
| 505 |
+
"learning_rate": 7.168222222222223e-05,
|
| 506 |
+
"loss": 1.943,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.731048121292023,
|
| 511 |
+
"grad_norm": 4.105598449707031,
|
| 512 |
+
"learning_rate": 7.112666666666668e-05,
|
| 513 |
+
"loss": 1.9403,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 24.060646011865526,
|
| 518 |
+
"grad_norm": 4.19888973236084,
|
| 519 |
+
"learning_rate": 7.057222222222223e-05,
|
| 520 |
+
"loss": 1.9306,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 24.390243902439025,
|
| 525 |
+
"grad_norm": 5.557919979095459,
|
| 526 |
+
"learning_rate": 7.001666666666667e-05,
|
| 527 |
+
"loss": 1.9055,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 24.719841793012524,
|
| 532 |
+
"grad_norm": 4.575863838195801,
|
| 533 |
+
"learning_rate": 6.946111111111111e-05,
|
| 534 |
+
"loss": 1.8855,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 25.049439683586026,
|
| 539 |
+
"grad_norm": 5.226344108581543,
|
| 540 |
+
"learning_rate": 6.890555555555556e-05,
|
| 541 |
+
"loss": 1.8906,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 25.379037574159526,
|
| 546 |
+
"grad_norm": 4.725679874420166,
|
| 547 |
+
"learning_rate": 6.835000000000001e-05,
|
| 548 |
+
"loss": 1.8643,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 25.708635464733025,
|
| 553 |
+
"grad_norm": 4.374075412750244,
|
| 554 |
+
"learning_rate": 6.779444444444444e-05,
|
| 555 |
+
"loss": 1.8558,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 26.038233355306527,
|
| 560 |
+
"grad_norm": 5.11503267288208,
|
| 561 |
+
"learning_rate": 6.72388888888889e-05,
|
| 562 |
+
"loss": 1.8685,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 26.367831245880026,
|
| 567 |
+
"grad_norm": 4.175240993499756,
|
| 568 |
+
"learning_rate": 6.668333333333333e-05,
|
| 569 |
+
"loss": 1.834,
|
| 570 |
+
"step": 40000
|
| 571 |
+
}
|
| 572 |
+
],
|
| 573 |
+
"logging_steps": 500,
|
| 574 |
+
"max_steps": 100000,
|
| 575 |
+
"num_input_tokens_seen": 0,
|
| 576 |
+
"num_train_epochs": 66,
|
| 577 |
+
"save_steps": 20000,
|
| 578 |
+
"stateful_callbacks": {
|
| 579 |
+
"TrainerControl": {
|
| 580 |
+
"args": {
|
| 581 |
+
"should_epoch_stop": false,
|
| 582 |
+
"should_evaluate": false,
|
| 583 |
+
"should_log": false,
|
| 584 |
+
"should_save": true,
|
| 585 |
+
"should_training_stop": false
|
| 586 |
+
},
|
| 587 |
+
"attributes": {}
|
| 588 |
+
}
|
| 589 |
+
},
|
| 590 |
+
"total_flos": 1.2648746163823411e+17,
|
| 591 |
+
"train_batch_size": 32,
|
| 592 |
+
"trial_name": null,
|
| 593 |
+
"trial_params": null
|
| 594 |
+
}
|
checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69df6ad8c68fb54108512e3e72f6cf8c86833f012b145d178a64ad70f75abaa
|
| 3 |
+
size 5368
|
checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-60000/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": 514,
|
| 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": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-60000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-60000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4dcf6da05e526ace446440b10fe553cd8be6991e42c050bc9dca052bb177155
|
| 3 |
+
size 334030264
|
checkpoint-60000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e109267b6feecb9bfef798550123530ebf98d3d80d05f3e09e2d73e95af12759
|
| 3 |
+
size 668124218
|
checkpoint-60000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9636b83fa0698133f6c17f49b4c9eb7ec5398dc2fc64d0472f73d710d30a9bb2
|
| 3 |
+
size 14244
|
checkpoint-60000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:939829cc80a0dce9d4b6f3e8afdb87f31032ac050e7ab06615bd8f1982a5dfea
|
| 3 |
+
size 988
|
checkpoint-60000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b27cc4fecdbdfefafa69cad7a386cf8bea73ebab0ab50ef1848580dba44c4ee
|
| 3 |
+
size 1064
|
checkpoint-60000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-60000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-60000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-60000/trainer_state.json
ADDED
|
@@ -0,0 +1,874 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.55174686882004,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 60000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3295978905735003,
|
| 14 |
+
"grad_norm": 2.8918700218200684,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.1735,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6591957811470006,
|
| 21 |
+
"grad_norm": 2.0813119411468506,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 8.4577,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.988793671720501,
|
| 28 |
+
"grad_norm": 1.871568202972412,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 7.6313,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.3183915622940012,
|
| 35 |
+
"grad_norm": 1.7127728462219238,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 7.3405,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.6479894528675016,
|
| 42 |
+
"grad_norm": 1.7611004114151,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 7.1579,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.977587343441002,
|
| 49 |
+
"grad_norm": 1.7559301853179932,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 7.0353,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.3071852340145025,
|
| 56 |
+
"grad_norm": 2.062741994857788,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 6.949,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.6367831245880025,
|
| 63 |
+
"grad_norm": 2.037240505218506,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 6.8905,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.966381015161503,
|
| 70 |
+
"grad_norm": 2.732247829437256,
|
| 71 |
+
"learning_rate": 4.5e-05,
|
| 72 |
+
"loss": 6.8433,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.2959789057350033,
|
| 77 |
+
"grad_norm": 2.648927927017212,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 6.7753,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.6255767963085037,
|
| 84 |
+
"grad_norm": 3.1528918743133545,
|
| 85 |
+
"learning_rate": 5.500000000000001e-05,
|
| 86 |
+
"loss": 6.747,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.955174686882004,
|
| 91 |
+
"grad_norm": 2.9101691246032715,
|
| 92 |
+
"learning_rate": 6e-05,
|
| 93 |
+
"loss": 6.7081,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.284772577455504,
|
| 98 |
+
"grad_norm": 2.407719612121582,
|
| 99 |
+
"learning_rate": 6.499000000000001e-05,
|
| 100 |
+
"loss": 6.6724,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.614370468029005,
|
| 105 |
+
"grad_norm": 1.8148102760314941,
|
| 106 |
+
"learning_rate": 6.999e-05,
|
| 107 |
+
"loss": 6.6584,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.943968358602505,
|
| 112 |
+
"grad_norm": 2.6724727153778076,
|
| 113 |
+
"learning_rate": 7.499e-05,
|
| 114 |
+
"loss": 6.6439,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.273566249176005,
|
| 119 |
+
"grad_norm": 2.199885368347168,
|
| 120 |
+
"learning_rate": 7.999000000000001e-05,
|
| 121 |
+
"loss": 6.592,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.603164139749506,
|
| 126 |
+
"grad_norm": 2.2242558002471924,
|
| 127 |
+
"learning_rate": 8.498e-05,
|
| 128 |
+
"loss": 6.5687,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.932762030323006,
|
| 133 |
+
"grad_norm": 3.0547144412994385,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 6.5339,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.262359920896507,
|
| 140 |
+
"grad_norm": 3.8027408123016357,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 6.4818,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.591957811470007,
|
| 147 |
+
"grad_norm": 2.3049635887145996,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 6.392,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.921555702043507,
|
| 154 |
+
"grad_norm": 3.5188333988189697,
|
| 155 |
+
"learning_rate": 9.944777777777778e-05,
|
| 156 |
+
"loss": 6.2095,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.251153592617007,
|
| 161 |
+
"grad_norm": 5.0908050537109375,
|
| 162 |
+
"learning_rate": 9.889222222222223e-05,
|
| 163 |
+
"loss": 5.8004,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.580751483190507,
|
| 168 |
+
"grad_norm": 4.9945068359375,
|
| 169 |
+
"learning_rate": 9.833777777777779e-05,
|
| 170 |
+
"loss": 5.3376,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.910349373764008,
|
| 175 |
+
"grad_norm": 4.765307426452637,
|
| 176 |
+
"learning_rate": 9.778222222222222e-05,
|
| 177 |
+
"loss": 4.9592,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 8.23994726433751,
|
| 182 |
+
"grad_norm": 4.015578269958496,
|
| 183 |
+
"learning_rate": 9.722666666666666e-05,
|
| 184 |
+
"loss": 4.5913,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.569545154911008,
|
| 189 |
+
"grad_norm": 4.644675254821777,
|
| 190 |
+
"learning_rate": 9.667111111111111e-05,
|
| 191 |
+
"loss": 4.3206,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.899143045484509,
|
| 196 |
+
"grad_norm": 3.8366589546203613,
|
| 197 |
+
"learning_rate": 9.611555555555556e-05,
|
| 198 |
+
"loss": 4.1122,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 9.22874093605801,
|
| 203 |
+
"grad_norm": 4.115426540374756,
|
| 204 |
+
"learning_rate": 9.556111111111112e-05,
|
| 205 |
+
"loss": 3.8972,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.558338826631509,
|
| 210 |
+
"grad_norm": 4.137101650238037,
|
| 211 |
+
"learning_rate": 9.500555555555555e-05,
|
| 212 |
+
"loss": 3.7381,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.88793671720501,
|
| 217 |
+
"grad_norm": 5.157057285308838,
|
| 218 |
+
"learning_rate": 9.445e-05,
|
| 219 |
+
"loss": 3.6142,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 10.21753460777851,
|
| 224 |
+
"grad_norm": 3.9190354347229004,
|
| 225 |
+
"learning_rate": 9.389444444444446e-05,
|
| 226 |
+
"loss": 3.4768,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.54713249835201,
|
| 231 |
+
"grad_norm": 3.799747943878174,
|
| 232 |
+
"learning_rate": 9.333888888888889e-05,
|
| 233 |
+
"loss": 3.3694,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.87673038892551,
|
| 238 |
+
"grad_norm": 4.951575756072998,
|
| 239 |
+
"learning_rate": 9.278333333333333e-05,
|
| 240 |
+
"loss": 3.2834,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 11.206328279499012,
|
| 245 |
+
"grad_norm": 3.807826042175293,
|
| 246 |
+
"learning_rate": 9.222777777777778e-05,
|
| 247 |
+
"loss": 3.176,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.53592617007251,
|
| 252 |
+
"grad_norm": 4.53897762298584,
|
| 253 |
+
"learning_rate": 9.167222222222223e-05,
|
| 254 |
+
"loss": 3.096,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.865524060646012,
|
| 259 |
+
"grad_norm": 4.1547980308532715,
|
| 260 |
+
"learning_rate": 9.111777777777779e-05,
|
| 261 |
+
"loss": 3.0208,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 12.195121951219512,
|
| 266 |
+
"grad_norm": 4.5414719581604,
|
| 267 |
+
"learning_rate": 9.056222222222222e-05,
|
| 268 |
+
"loss": 2.9412,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.524719841793013,
|
| 273 |
+
"grad_norm": 4.638998508453369,
|
| 274 |
+
"learning_rate": 9.000666666666667e-05,
|
| 275 |
+
"loss": 2.8768,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.854317732366512,
|
| 280 |
+
"grad_norm": 3.492238759994507,
|
| 281 |
+
"learning_rate": 8.945111111111112e-05,
|
| 282 |
+
"loss": 2.8319,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 13.183915622940013,
|
| 287 |
+
"grad_norm": 3.963812828063965,
|
| 288 |
+
"learning_rate": 8.889666666666668e-05,
|
| 289 |
+
"loss": 2.7481,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.513513513513514,
|
| 294 |
+
"grad_norm": 4.802724361419678,
|
| 295 |
+
"learning_rate": 8.834111111111112e-05,
|
| 296 |
+
"loss": 2.7044,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.843111404087013,
|
| 301 |
+
"grad_norm": 4.897942066192627,
|
| 302 |
+
"learning_rate": 8.778555555555555e-05,
|
| 303 |
+
"loss": 2.6523,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 14.172709294660514,
|
| 308 |
+
"grad_norm": 4.577375411987305,
|
| 309 |
+
"learning_rate": 8.723e-05,
|
| 310 |
+
"loss": 2.6131,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.502307185234015,
|
| 315 |
+
"grad_norm": 4.424295902252197,
|
| 316 |
+
"learning_rate": 8.667444444444444e-05,
|
| 317 |
+
"loss": 2.5573,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 14.831905075807516,
|
| 322 |
+
"grad_norm": 4.2922749519348145,
|
| 323 |
+
"learning_rate": 8.612e-05,
|
| 324 |
+
"loss": 2.5337,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 15.161502966381015,
|
| 329 |
+
"grad_norm": 4.366146564483643,
|
| 330 |
+
"learning_rate": 8.556444444444445e-05,
|
| 331 |
+
"loss": 2.4788,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.491100856954516,
|
| 336 |
+
"grad_norm": 4.874686241149902,
|
| 337 |
+
"learning_rate": 8.50088888888889e-05,
|
| 338 |
+
"loss": 2.4399,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.820698747528017,
|
| 343 |
+
"grad_norm": 5.1893463134765625,
|
| 344 |
+
"learning_rate": 8.445333333333333e-05,
|
| 345 |
+
"loss": 2.4304,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.150296638101516,
|
| 350 |
+
"grad_norm": 4.169196605682373,
|
| 351 |
+
"learning_rate": 8.389888888888889e-05,
|
| 352 |
+
"loss": 2.3779,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 16.47989452867502,
|
| 357 |
+
"grad_norm": 4.332625865936279,
|
| 358 |
+
"learning_rate": 8.334333333333334e-05,
|
| 359 |
+
"loss": 2.3538,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.809492419248517,
|
| 364 |
+
"grad_norm": 5.98911190032959,
|
| 365 |
+
"learning_rate": 8.278777777777779e-05,
|
| 366 |
+
"loss": 2.3304,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 17.139090309822016,
|
| 371 |
+
"grad_norm": 4.644032001495361,
|
| 372 |
+
"learning_rate": 8.223222222222223e-05,
|
| 373 |
+
"loss": 2.3024,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 17.46868820039552,
|
| 378 |
+
"grad_norm": 4.4497971534729,
|
| 379 |
+
"learning_rate": 8.167777777777778e-05,
|
| 380 |
+
"loss": 2.2653,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.798286090969018,
|
| 385 |
+
"grad_norm": 3.7030065059661865,
|
| 386 |
+
"learning_rate": 8.112222222222222e-05,
|
| 387 |
+
"loss": 2.2525,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 18.127883981542517,
|
| 392 |
+
"grad_norm": 4.448596000671387,
|
| 393 |
+
"learning_rate": 8.056777777777779e-05,
|
| 394 |
+
"loss": 2.2154,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 18.45748187211602,
|
| 399 |
+
"grad_norm": 4.464804649353027,
|
| 400 |
+
"learning_rate": 8.001222222222222e-05,
|
| 401 |
+
"loss": 2.2012,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.78707976268952,
|
| 406 |
+
"grad_norm": 4.686955451965332,
|
| 407 |
+
"learning_rate": 7.945666666666667e-05,
|
| 408 |
+
"loss": 2.1827,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 19.116677653263018,
|
| 413 |
+
"grad_norm": 3.8840394020080566,
|
| 414 |
+
"learning_rate": 7.890111111111111e-05,
|
| 415 |
+
"loss": 2.1409,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 19.44627554383652,
|
| 420 |
+
"grad_norm": 3.527129888534546,
|
| 421 |
+
"learning_rate": 7.834555555555556e-05,
|
| 422 |
+
"loss": 2.1215,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.77587343441002,
|
| 427 |
+
"grad_norm": 5.817971706390381,
|
| 428 |
+
"learning_rate": 7.779000000000001e-05,
|
| 429 |
+
"loss": 2.1161,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 20.10547132498352,
|
| 434 |
+
"grad_norm": 5.153094291687012,
|
| 435 |
+
"learning_rate": 7.723444444444444e-05,
|
| 436 |
+
"loss": 2.0967,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 20.43506921555702,
|
| 441 |
+
"grad_norm": 5.022122859954834,
|
| 442 |
+
"learning_rate": 7.667888888888889e-05,
|
| 443 |
+
"loss": 2.0789,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.76466710613052,
|
| 448 |
+
"grad_norm": 4.343278884887695,
|
| 449 |
+
"learning_rate": 7.612444444444444e-05,
|
| 450 |
+
"loss": 2.0725,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 21.09426499670402,
|
| 455 |
+
"grad_norm": 5.50627326965332,
|
| 456 |
+
"learning_rate": 7.556888888888889e-05,
|
| 457 |
+
"loss": 2.0538,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 21.423862887277522,
|
| 462 |
+
"grad_norm": 4.042550563812256,
|
| 463 |
+
"learning_rate": 7.501333333333333e-05,
|
| 464 |
+
"loss": 2.0334,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.75346077785102,
|
| 469 |
+
"grad_norm": 5.352642059326172,
|
| 470 |
+
"learning_rate": 7.445777777777778e-05,
|
| 471 |
+
"loss": 2.0204,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 22.08305866842452,
|
| 476 |
+
"grad_norm": 4.7281494140625,
|
| 477 |
+
"learning_rate": 7.390333333333333e-05,
|
| 478 |
+
"loss": 2.0143,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 22.412656558998023,
|
| 483 |
+
"grad_norm": 5.191075801849365,
|
| 484 |
+
"learning_rate": 7.334777777777778e-05,
|
| 485 |
+
"loss": 1.9848,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.742254449571522,
|
| 490 |
+
"grad_norm": 3.772347927093506,
|
| 491 |
+
"learning_rate": 7.279222222222222e-05,
|
| 492 |
+
"loss": 1.9792,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 23.071852340145025,
|
| 497 |
+
"grad_norm": 4.231102466583252,
|
| 498 |
+
"learning_rate": 7.223666666666667e-05,
|
| 499 |
+
"loss": 1.9795,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 23.401450230718524,
|
| 504 |
+
"grad_norm": 4.547638416290283,
|
| 505 |
+
"learning_rate": 7.168222222222223e-05,
|
| 506 |
+
"loss": 1.943,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.731048121292023,
|
| 511 |
+
"grad_norm": 4.105598449707031,
|
| 512 |
+
"learning_rate": 7.112666666666668e-05,
|
| 513 |
+
"loss": 1.9403,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 24.060646011865526,
|
| 518 |
+
"grad_norm": 4.19888973236084,
|
| 519 |
+
"learning_rate": 7.057222222222223e-05,
|
| 520 |
+
"loss": 1.9306,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 24.390243902439025,
|
| 525 |
+
"grad_norm": 5.557919979095459,
|
| 526 |
+
"learning_rate": 7.001666666666667e-05,
|
| 527 |
+
"loss": 1.9055,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 24.719841793012524,
|
| 532 |
+
"grad_norm": 4.575863838195801,
|
| 533 |
+
"learning_rate": 6.946111111111111e-05,
|
| 534 |
+
"loss": 1.8855,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 25.049439683586026,
|
| 539 |
+
"grad_norm": 5.226344108581543,
|
| 540 |
+
"learning_rate": 6.890555555555556e-05,
|
| 541 |
+
"loss": 1.8906,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 25.379037574159526,
|
| 546 |
+
"grad_norm": 4.725679874420166,
|
| 547 |
+
"learning_rate": 6.835000000000001e-05,
|
| 548 |
+
"loss": 1.8643,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 25.708635464733025,
|
| 553 |
+
"grad_norm": 4.374075412750244,
|
| 554 |
+
"learning_rate": 6.779444444444444e-05,
|
| 555 |
+
"loss": 1.8558,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 26.038233355306527,
|
| 560 |
+
"grad_norm": 5.11503267288208,
|
| 561 |
+
"learning_rate": 6.72388888888889e-05,
|
| 562 |
+
"loss": 1.8685,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 26.367831245880026,
|
| 567 |
+
"grad_norm": 4.175240993499756,
|
| 568 |
+
"learning_rate": 6.668333333333333e-05,
|
| 569 |
+
"loss": 1.834,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 26.697429136453525,
|
| 574 |
+
"grad_norm": 5.351263999938965,
|
| 575 |
+
"learning_rate": 6.61288888888889e-05,
|
| 576 |
+
"loss": 1.8337,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 27.027027027027028,
|
| 581 |
+
"grad_norm": 4.664134979248047,
|
| 582 |
+
"learning_rate": 6.557333333333332e-05,
|
| 583 |
+
"loss": 1.8419,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 27.356624917600527,
|
| 588 |
+
"grad_norm": 4.658705711364746,
|
| 589 |
+
"learning_rate": 6.501777777777777e-05,
|
| 590 |
+
"loss": 1.7938,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 27.686222808174026,
|
| 595 |
+
"grad_norm": 4.4617228507995605,
|
| 596 |
+
"learning_rate": 6.446222222222223e-05,
|
| 597 |
+
"loss": 1.8047,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 28.01582069874753,
|
| 602 |
+
"grad_norm": 4.475608825683594,
|
| 603 |
+
"learning_rate": 6.390666666666668e-05,
|
| 604 |
+
"loss": 1.7869,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 28.345418589321028,
|
| 609 |
+
"grad_norm": 4.420760631561279,
|
| 610 |
+
"learning_rate": 6.335222222222222e-05,
|
| 611 |
+
"loss": 1.7748,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 28.675016479894527,
|
| 616 |
+
"grad_norm": 5.114872455596924,
|
| 617 |
+
"learning_rate": 6.279666666666667e-05,
|
| 618 |
+
"loss": 1.7581,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 29.00461437046803,
|
| 623 |
+
"grad_norm": 3.7333712577819824,
|
| 624 |
+
"learning_rate": 6.224111111111112e-05,
|
| 625 |
+
"loss": 1.768,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 29.33421226104153,
|
| 630 |
+
"grad_norm": 4.306798934936523,
|
| 631 |
+
"learning_rate": 6.168555555555557e-05,
|
| 632 |
+
"loss": 1.7278,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 29.66381015161503,
|
| 637 |
+
"grad_norm": 4.891313552856445,
|
| 638 |
+
"learning_rate": 6.113111111111111e-05,
|
| 639 |
+
"loss": 1.7436,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 29.99340804218853,
|
| 644 |
+
"grad_norm": 4.63929557800293,
|
| 645 |
+
"learning_rate": 6.057555555555556e-05,
|
| 646 |
+
"loss": 1.7448,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 30.32300593276203,
|
| 651 |
+
"grad_norm": 4.462540149688721,
|
| 652 |
+
"learning_rate": 6.0021111111111116e-05,
|
| 653 |
+
"loss": 1.7059,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 30.652603823335532,
|
| 658 |
+
"grad_norm": 4.313077449798584,
|
| 659 |
+
"learning_rate": 5.9465555555555567e-05,
|
| 660 |
+
"loss": 1.7273,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 30.98220171390903,
|
| 665 |
+
"grad_norm": 3.960693359375,
|
| 666 |
+
"learning_rate": 5.891e-05,
|
| 667 |
+
"loss": 1.7157,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 31.31179960448253,
|
| 672 |
+
"grad_norm": 4.755917549133301,
|
| 673 |
+
"learning_rate": 5.835444444444445e-05,
|
| 674 |
+
"loss": 1.6931,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 31.641397495056033,
|
| 679 |
+
"grad_norm": 4.8950042724609375,
|
| 680 |
+
"learning_rate": 5.779888888888889e-05,
|
| 681 |
+
"loss": 1.6889,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 31.970995385629532,
|
| 686 |
+
"grad_norm": 3.8848912715911865,
|
| 687 |
+
"learning_rate": 5.7243333333333335e-05,
|
| 688 |
+
"loss": 1.6881,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 32.30059327620303,
|
| 693 |
+
"grad_norm": 4.386871337890625,
|
| 694 |
+
"learning_rate": 5.6687777777777785e-05,
|
| 695 |
+
"loss": 1.6634,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 32.630191166776534,
|
| 700 |
+
"grad_norm": 4.7473464012146,
|
| 701 |
+
"learning_rate": 5.613222222222222e-05,
|
| 702 |
+
"loss": 1.6547,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 32.95978905735004,
|
| 707 |
+
"grad_norm": 4.609119892120361,
|
| 708 |
+
"learning_rate": 5.5577777777777784e-05,
|
| 709 |
+
"loss": 1.6622,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 33.28938694792353,
|
| 714 |
+
"grad_norm": 4.484665393829346,
|
| 715 |
+
"learning_rate": 5.502222222222222e-05,
|
| 716 |
+
"loss": 1.6462,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 33.618984838497035,
|
| 721 |
+
"grad_norm": 4.362062931060791,
|
| 722 |
+
"learning_rate": 5.4466666666666665e-05,
|
| 723 |
+
"loss": 1.638,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 33.94858272907054,
|
| 728 |
+
"grad_norm": 5.697278022766113,
|
| 729 |
+
"learning_rate": 5.3911111111111115e-05,
|
| 730 |
+
"loss": 1.6494,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 34.27818061964403,
|
| 735 |
+
"grad_norm": 5.001323223114014,
|
| 736 |
+
"learning_rate": 5.3356666666666663e-05,
|
| 737 |
+
"loss": 1.6304,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 34.607778510217535,
|
| 742 |
+
"grad_norm": 4.780933856964111,
|
| 743 |
+
"learning_rate": 5.2801111111111114e-05,
|
| 744 |
+
"loss": 1.6214,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 34.93737640079104,
|
| 749 |
+
"grad_norm": 4.25840425491333,
|
| 750 |
+
"learning_rate": 5.224555555555556e-05,
|
| 751 |
+
"loss": 1.6209,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 35.266974291364534,
|
| 756 |
+
"grad_norm": 3.9229302406311035,
|
| 757 |
+
"learning_rate": 5.169000000000001e-05,
|
| 758 |
+
"loss": 1.5934,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 35.596572181938036,
|
| 763 |
+
"grad_norm": 4.396152019500732,
|
| 764 |
+
"learning_rate": 5.1135555555555556e-05,
|
| 765 |
+
"loss": 1.5966,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 35.92617007251154,
|
| 770 |
+
"grad_norm": 4.942046165466309,
|
| 771 |
+
"learning_rate": 5.058000000000001e-05,
|
| 772 |
+
"loss": 1.591,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 36.255767963085034,
|
| 777 |
+
"grad_norm": 4.5848846435546875,
|
| 778 |
+
"learning_rate": 5.002444444444445e-05,
|
| 779 |
+
"loss": 1.5758,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 36.58536585365854,
|
| 784 |
+
"grad_norm": 5.14020299911499,
|
| 785 |
+
"learning_rate": 4.9468888888888894e-05,
|
| 786 |
+
"loss": 1.578,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 36.91496374423204,
|
| 791 |
+
"grad_norm": 3.547346353530884,
|
| 792 |
+
"learning_rate": 4.891333333333333e-05,
|
| 793 |
+
"loss": 1.5778,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 37.244561634805535,
|
| 798 |
+
"grad_norm": 4.23244047164917,
|
| 799 |
+
"learning_rate": 4.835888888888889e-05,
|
| 800 |
+
"loss": 1.5584,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 37.57415952537904,
|
| 805 |
+
"grad_norm": 4.20224666595459,
|
| 806 |
+
"learning_rate": 4.780333333333333e-05,
|
| 807 |
+
"loss": 1.5564,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 37.90375741595254,
|
| 812 |
+
"grad_norm": 5.5531229972839355,
|
| 813 |
+
"learning_rate": 4.724777777777778e-05,
|
| 814 |
+
"loss": 1.5509,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 38.233355306526036,
|
| 819 |
+
"grad_norm": 4.247383117675781,
|
| 820 |
+
"learning_rate": 4.6692222222222224e-05,
|
| 821 |
+
"loss": 1.5491,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 38.56295319709954,
|
| 826 |
+
"grad_norm": 4.918506622314453,
|
| 827 |
+
"learning_rate": 4.613777777777778e-05,
|
| 828 |
+
"loss": 1.5382,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 38.89255108767304,
|
| 833 |
+
"grad_norm": 5.86004114151001,
|
| 834 |
+
"learning_rate": 4.558222222222222e-05,
|
| 835 |
+
"loss": 1.5389,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 39.22214897824654,
|
| 840 |
+
"grad_norm": 4.52742862701416,
|
| 841 |
+
"learning_rate": 4.502666666666667e-05,
|
| 842 |
+
"loss": 1.5182,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 39.55174686882004,
|
| 847 |
+
"grad_norm": 4.052803993225098,
|
| 848 |
+
"learning_rate": 4.447111111111111e-05,
|
| 849 |
+
"loss": 1.5221,
|
| 850 |
+
"step": 60000
|
| 851 |
+
}
|
| 852 |
+
],
|
| 853 |
+
"logging_steps": 500,
|
| 854 |
+
"max_steps": 100000,
|
| 855 |
+
"num_input_tokens_seen": 0,
|
| 856 |
+
"num_train_epochs": 66,
|
| 857 |
+
"save_steps": 20000,
|
| 858 |
+
"stateful_callbacks": {
|
| 859 |
+
"TrainerControl": {
|
| 860 |
+
"args": {
|
| 861 |
+
"should_epoch_stop": false,
|
| 862 |
+
"should_evaluate": false,
|
| 863 |
+
"should_log": false,
|
| 864 |
+
"should_save": true,
|
| 865 |
+
"should_training_stop": false
|
| 866 |
+
},
|
| 867 |
+
"attributes": {}
|
| 868 |
+
}
|
| 869 |
+
},
|
| 870 |
+
"total_flos": 1.8971186205220454e+17,
|
| 871 |
+
"train_batch_size": 32,
|
| 872 |
+
"trial_name": null,
|
| 873 |
+
"trial_params": null
|
| 874 |
+
}
|