Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +10 -0
- deberta_v3_base/fold_0/best/added_tokens.json +3 -0
- deberta_v3_base/fold_0/best/config.json +37 -0
- deberta_v3_base/fold_0/best/model.safetensors +3 -0
- deberta_v3_base/fold_0/best/special_tokens_map.json +15 -0
- deberta_v3_base/fold_0/best/spm.model +3 -0
- deberta_v3_base/fold_0/best/tokenizer_config.json +59 -0
- deberta_v3_base/fold_0/best/training_args.bin +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/added_tokens.json +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/config.json +37 -0
- deberta_v3_base/fold_0/checkpoint-23218/model.safetensors +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/optimizer.pt +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/rng_state.pth +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/scaler.pt +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/scheduler.pt +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/special_tokens_map.json +15 -0
- deberta_v3_base/fold_0/checkpoint-23218/spm.model +3 -0
- deberta_v3_base/fold_0/checkpoint-23218/tokenizer_config.json +59 -0
- deberta_v3_base/fold_0/checkpoint-23218/trainer_state.json +3282 -0
- deberta_v3_base/fold_0/checkpoint-23218/training_args.bin +3 -0
- deberta_v3_base/fold_0/checkpoint-500/added_tokens.json +3 -0
- deberta_v3_base/fold_0/checkpoint-500/config.json +37 -0
- deberta_v3_base/fold_0/checkpoint-500/model.safetensors +3 -0
- deberta_v3_base/fold_0/checkpoint-500/optimizer.pt +3 -0
- deberta_v3_base/fold_0/checkpoint-500/rng_state_0.pth +3 -0
- deberta_v3_base/fold_0/checkpoint-500/rng_state_1.pth +3 -0
- deberta_v3_base/fold_0/checkpoint-500/rng_state_2.pth +3 -0
- deberta_v3_base/fold_0/checkpoint-500/rng_state_3.pth +3 -0
- deberta_v3_base/fold_0/checkpoint-500/scheduler.pt +3 -0
- deberta_v3_base/fold_0/checkpoint-500/special_tokens_map.json +15 -0
- deberta_v3_base/fold_0/checkpoint-500/spm.model +3 -0
- deberta_v3_base/fold_0/checkpoint-500/tokenizer_config.json +59 -0
- deberta_v3_base/fold_0/checkpoint-500/trainer_state.json +122 -0
- deberta_v3_base/fold_0/checkpoint-500/training_args.bin +3 -0
- deberta_v3_base/fold_1/best/added_tokens.json +3 -0
- deberta_v3_base/fold_1/best/config.json +37 -0
- deberta_v3_base/fold_1/best/model.safetensors +3 -0
- deberta_v3_base/fold_1/best/special_tokens_map.json +15 -0
- deberta_v3_base/fold_1/best/spm.model +3 -0
- deberta_v3_base/fold_1/best/tokenizer_config.json +59 -0
- deberta_v3_base/fold_1/best/training_args.bin +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/added_tokens.json +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/config.json +37 -0
- deberta_v3_base/fold_1/checkpoint-1000/model.safetensors +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/optimizer.pt +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/rng_state_0.pth +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/rng_state_1.pth +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/rng_state_2.pth +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/rng_state_3.pth +3 -0
- deberta_v3_base/fold_1/checkpoint-1000/scheduler.pt +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
training_metrics/fold_0/plot_gates.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
training_metrics/fold_0/plot_losses.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
training_metrics/fold_1/plot_gates.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
training_metrics/fold_1/plot_losses.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
training_metrics/fold_2/plot_gates.png filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
training_metrics/fold_2/plot_losses.png filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
training_metrics/fold_3/plot_gates.png filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
training_metrics/fold_3/plot_losses.png filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
training_metrics/fold_4/plot_gates.png filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
training_metrics/fold_4/plot_losses.png filter=lfs diff=lfs merge=lfs -text
|
deberta_v3_base/fold_0/best/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
deberta_v3_base/fold_0/best/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 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-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"relative_attention": true,
|
| 33 |
+
"share_att_key": true,
|
| 34 |
+
"transformers_version": "4.57.3",
|
| 35 |
+
"type_vocab_size": 0,
|
| 36 |
+
"vocab_size": 128100
|
| 37 |
+
}
|
deberta_v3_base/fold_0/best/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3f4b16f57b323c3e5d6b0e0f38b23da59fc659269d405a4068d633ec12a9b74
|
| 3 |
+
size 737719272
|
deberta_v3_base/fold_0/best/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
deberta_v3_base/fold_0/best/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
deberta_v3_base/fold_0/best/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
deberta_v3_base/fold_0/best/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54d713a9b7f7addbb556c6778ecce8aeea6e654064eaea3f3b331cd2450781e3
|
| 3 |
+
size 5905
|
deberta_v3_base/fold_0/checkpoint-23218/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
deberta_v3_base/fold_0/checkpoint-23218/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 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-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"relative_attention": true,
|
| 33 |
+
"share_att_key": true,
|
| 34 |
+
"transformers_version": "4.57.3",
|
| 35 |
+
"type_vocab_size": 0,
|
| 36 |
+
"vocab_size": 128100
|
| 37 |
+
}
|
deberta_v3_base/fold_0/checkpoint-23218/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bde6233d1902b9fbad7b75102653faf6127284d6b3232e30910bad6a6e3a871
|
| 3 |
+
size 737719272
|
deberta_v3_base/fold_0/checkpoint-23218/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:467d899ad1bf55f50bdb309f7dfc40eee279f36ec7249f409352ba2086ce6d8c
|
| 3 |
+
size 1475561675
|
deberta_v3_base/fold_0/checkpoint-23218/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a93ab7c781d7b87ad738cb8efa662921f3e4376619d5ab341e1f558942bf96e
|
| 3 |
+
size 14645
|
deberta_v3_base/fold_0/checkpoint-23218/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ef085d3d6964c5245b507d56f153e70581912d4f0448b733476c0eb7a334f0d
|
| 3 |
+
size 1383
|
deberta_v3_base/fold_0/checkpoint-23218/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938625739f12d2c18adf315d97cb31f4120832101609f1298ef3d25d7a442050
|
| 3 |
+
size 1465
|
deberta_v3_base/fold_0/checkpoint-23218/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
deberta_v3_base/fold_0/checkpoint-23218/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
deberta_v3_base/fold_0/checkpoint-23218/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
deberta_v3_base/fold_0/checkpoint-23218/trainer_state.json
ADDED
|
@@ -0,0 +1,3282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 23218,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004307003187182358,
|
| 14 |
+
"grad_norm": 0.7000011801719666,
|
| 15 |
+
"learning_rate": 4.220499569336779e-07,
|
| 16 |
+
"loss": 0.6738,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008614006374364717,
|
| 21 |
+
"grad_norm": 0.978523313999176,
|
| 22 |
+
"learning_rate": 8.527131782945737e-07,
|
| 23 |
+
"loss": 0.6617,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.012921009561547075,
|
| 28 |
+
"grad_norm": 1.4331661462783813,
|
| 29 |
+
"learning_rate": 1.2833763996554696e-06,
|
| 30 |
+
"loss": 0.6316,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.017228012748729434,
|
| 35 |
+
"grad_norm": 2.004758596420288,
|
| 36 |
+
"learning_rate": 1.7140396210163654e-06,
|
| 37 |
+
"loss": 0.5778,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.021535015935911794,
|
| 42 |
+
"grad_norm": 2.6827335357666016,
|
| 43 |
+
"learning_rate": 2.144702842377261e-06,
|
| 44 |
+
"loss": 0.3367,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02584201912309415,
|
| 49 |
+
"grad_norm": 1.5063152313232422,
|
| 50 |
+
"learning_rate": 2.575366063738157e-06,
|
| 51 |
+
"loss": 0.2202,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03014902231027651,
|
| 56 |
+
"grad_norm": 4.345446586608887,
|
| 57 |
+
"learning_rate": 3.006029285099053e-06,
|
| 58 |
+
"loss": 0.1849,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03445602549745887,
|
| 63 |
+
"grad_norm": 6.083446979522705,
|
| 64 |
+
"learning_rate": 3.436692506459949e-06,
|
| 65 |
+
"loss": 0.1669,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.038763028684641224,
|
| 70 |
+
"grad_norm": 8.122875213623047,
|
| 71 |
+
"learning_rate": 3.867355727820845e-06,
|
| 72 |
+
"loss": 0.1495,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04307003187182359,
|
| 77 |
+
"grad_norm": 6.156876564025879,
|
| 78 |
+
"learning_rate": 4.2980189491817404e-06,
|
| 79 |
+
"loss": 0.1543,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.047377035059005944,
|
| 84 |
+
"grad_norm": 3.276002883911133,
|
| 85 |
+
"learning_rate": 4.728682170542636e-06,
|
| 86 |
+
"loss": 0.1284,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0516840382461883,
|
| 91 |
+
"grad_norm": 1.8661900758743286,
|
| 92 |
+
"learning_rate": 5.159345391903532e-06,
|
| 93 |
+
"loss": 0.133,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.055991041433370664,
|
| 98 |
+
"grad_norm": 1.5809457302093506,
|
| 99 |
+
"learning_rate": 5.590008613264428e-06,
|
| 100 |
+
"loss": 0.1288,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.06029804462055302,
|
| 105 |
+
"grad_norm": 1.736406683921814,
|
| 106 |
+
"learning_rate": 6.020671834625324e-06,
|
| 107 |
+
"loss": 0.1251,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.06460504780773538,
|
| 112 |
+
"grad_norm": 1.6068320274353027,
|
| 113 |
+
"learning_rate": 6.45133505598622e-06,
|
| 114 |
+
"loss": 0.1302,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06891205099491773,
|
| 119 |
+
"grad_norm": 1.194906234741211,
|
| 120 |
+
"learning_rate": 6.881998277347115e-06,
|
| 121 |
+
"loss": 0.1296,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07321905418210009,
|
| 126 |
+
"grad_norm": 2.286773681640625,
|
| 127 |
+
"learning_rate": 7.312661498708011e-06,
|
| 128 |
+
"loss": 0.1182,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07752605736928245,
|
| 133 |
+
"grad_norm": 3.3516457080841064,
|
| 134 |
+
"learning_rate": 7.743324720068907e-06,
|
| 135 |
+
"loss": 0.1213,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08183306055646482,
|
| 140 |
+
"grad_norm": 1.7491710186004639,
|
| 141 |
+
"learning_rate": 8.173987941429803e-06,
|
| 142 |
+
"loss": 0.115,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.08614006374364717,
|
| 147 |
+
"grad_norm": 8.332209587097168,
|
| 148 |
+
"learning_rate": 8.604651162790698e-06,
|
| 149 |
+
"loss": 0.1217,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.09044706693082953,
|
| 154 |
+
"grad_norm": 6.165684223175049,
|
| 155 |
+
"learning_rate": 9.035314384151595e-06,
|
| 156 |
+
"loss": 0.1049,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.09475407011801189,
|
| 161 |
+
"grad_norm": 2.594433069229126,
|
| 162 |
+
"learning_rate": 9.46597760551249e-06,
|
| 163 |
+
"loss": 0.0979,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.09906107330519424,
|
| 168 |
+
"grad_norm": 4.0021891593933105,
|
| 169 |
+
"learning_rate": 9.896640826873386e-06,
|
| 170 |
+
"loss": 0.1245,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1033680764923766,
|
| 175 |
+
"grad_norm": 2.933079957962036,
|
| 176 |
+
"learning_rate": 1.032730404823428e-05,
|
| 177 |
+
"loss": 0.1108,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.10767507967955896,
|
| 182 |
+
"grad_norm": 0.9269832968711853,
|
| 183 |
+
"learning_rate": 1.0757967269595177e-05,
|
| 184 |
+
"loss": 0.1124,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.11198208286674133,
|
| 189 |
+
"grad_norm": 2.196971893310547,
|
| 190 |
+
"learning_rate": 1.1188630490956073e-05,
|
| 191 |
+
"loss": 0.1105,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.11628908605392368,
|
| 196 |
+
"grad_norm": 0.5897941589355469,
|
| 197 |
+
"learning_rate": 1.1619293712316968e-05,
|
| 198 |
+
"loss": 0.1051,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.12059608924110604,
|
| 203 |
+
"grad_norm": 2.434842348098755,
|
| 204 |
+
"learning_rate": 1.2049956933677865e-05,
|
| 205 |
+
"loss": 0.1036,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1249030924282884,
|
| 210 |
+
"grad_norm": 2.4015684127807617,
|
| 211 |
+
"learning_rate": 1.2480620155038761e-05,
|
| 212 |
+
"loss": 0.088,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.12921009561547075,
|
| 217 |
+
"grad_norm": 2.0369980335235596,
|
| 218 |
+
"learning_rate": 1.2911283376399657e-05,
|
| 219 |
+
"loss": 0.0976,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1335170988026531,
|
| 224 |
+
"grad_norm": 3.795889377593994,
|
| 225 |
+
"learning_rate": 1.3341946597760554e-05,
|
| 226 |
+
"loss": 0.0993,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.13782410198983547,
|
| 231 |
+
"grad_norm": 1.6375834941864014,
|
| 232 |
+
"learning_rate": 1.3772609819121447e-05,
|
| 233 |
+
"loss": 0.1216,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.14213110517701782,
|
| 238 |
+
"grad_norm": 1.1701602935791016,
|
| 239 |
+
"learning_rate": 1.4203273040482343e-05,
|
| 240 |
+
"loss": 0.0994,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.14643810836420018,
|
| 245 |
+
"grad_norm": 1.2350437641143799,
|
| 246 |
+
"learning_rate": 1.463393626184324e-05,
|
| 247 |
+
"loss": 0.0933,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.15074511155138254,
|
| 252 |
+
"grad_norm": 4.211219787597656,
|
| 253 |
+
"learning_rate": 1.5064599483204136e-05,
|
| 254 |
+
"loss": 0.1026,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1550521147385649,
|
| 259 |
+
"grad_norm": 1.7111949920654297,
|
| 260 |
+
"learning_rate": 1.549526270456503e-05,
|
| 261 |
+
"loss": 0.0904,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.15935911792574725,
|
| 266 |
+
"grad_norm": 3.583889961242676,
|
| 267 |
+
"learning_rate": 1.5925925925925926e-05,
|
| 268 |
+
"loss": 0.0893,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.16366612111292964,
|
| 273 |
+
"grad_norm": 5.318212032318115,
|
| 274 |
+
"learning_rate": 1.6356589147286824e-05,
|
| 275 |
+
"loss": 0.1,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.167973124300112,
|
| 280 |
+
"grad_norm": 4.480594158172607,
|
| 281 |
+
"learning_rate": 1.678725236864772e-05,
|
| 282 |
+
"loss": 0.112,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.17228012748729435,
|
| 287 |
+
"grad_norm": 0.8804246187210083,
|
| 288 |
+
"learning_rate": 1.7217915590008613e-05,
|
| 289 |
+
"loss": 0.099,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.1765871306744767,
|
| 294 |
+
"grad_norm": 2.0178182125091553,
|
| 295 |
+
"learning_rate": 1.764857881136951e-05,
|
| 296 |
+
"loss": 0.1037,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.18089413386165906,
|
| 301 |
+
"grad_norm": 4.215595722198486,
|
| 302 |
+
"learning_rate": 1.8079242032730406e-05,
|
| 303 |
+
"loss": 0.1092,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.18520113704884142,
|
| 308 |
+
"grad_norm": 1.1017696857452393,
|
| 309 |
+
"learning_rate": 1.85099052540913e-05,
|
| 310 |
+
"loss": 0.0962,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.18950814023602378,
|
| 315 |
+
"grad_norm": 2.0355255603790283,
|
| 316 |
+
"learning_rate": 1.89405684754522e-05,
|
| 317 |
+
"loss": 0.1077,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.19381514342320613,
|
| 322 |
+
"grad_norm": 3.2584192752838135,
|
| 323 |
+
"learning_rate": 1.9371231696813094e-05,
|
| 324 |
+
"loss": 0.0942,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1981221466103885,
|
| 329 |
+
"grad_norm": 1.0216509103775024,
|
| 330 |
+
"learning_rate": 1.980189491817399e-05,
|
| 331 |
+
"loss": 0.0813,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.20242914979757085,
|
| 336 |
+
"grad_norm": 3.8075778484344482,
|
| 337 |
+
"learning_rate": 1.997415773353752e-05,
|
| 338 |
+
"loss": 0.0959,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2067361529847532,
|
| 343 |
+
"grad_norm": 2.6191654205322266,
|
| 344 |
+
"learning_rate": 1.9926301684532928e-05,
|
| 345 |
+
"loss": 0.0848,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.21104315617193556,
|
| 350 |
+
"grad_norm": 1.4009710550308228,
|
| 351 |
+
"learning_rate": 1.987844563552833e-05,
|
| 352 |
+
"loss": 0.0831,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.21535015935911792,
|
| 357 |
+
"grad_norm": 0.7992962002754211,
|
| 358 |
+
"learning_rate": 1.983058958652374e-05,
|
| 359 |
+
"loss": 0.0932,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.21965716254630027,
|
| 364 |
+
"grad_norm": 1.4398599863052368,
|
| 365 |
+
"learning_rate": 1.9782733537519143e-05,
|
| 366 |
+
"loss": 0.0871,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.22396416573348266,
|
| 371 |
+
"grad_norm": 1.2562077045440674,
|
| 372 |
+
"learning_rate": 1.973487748851455e-05,
|
| 373 |
+
"loss": 0.1002,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.228271168920665,
|
| 378 |
+
"grad_norm": 1.0918809175491333,
|
| 379 |
+
"learning_rate": 1.9687021439509954e-05,
|
| 380 |
+
"loss": 0.0963,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.23257817210784737,
|
| 385 |
+
"grad_norm": 1.0898282527923584,
|
| 386 |
+
"learning_rate": 1.963916539050536e-05,
|
| 387 |
+
"loss": 0.0979,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.23688517529502973,
|
| 392 |
+
"grad_norm": 1.3931770324707031,
|
| 393 |
+
"learning_rate": 1.9591309341500768e-05,
|
| 394 |
+
"loss": 0.0892,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.24119217848221208,
|
| 399 |
+
"grad_norm": 1.2146763801574707,
|
| 400 |
+
"learning_rate": 1.9543453292496172e-05,
|
| 401 |
+
"loss": 0.0871,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.24549918166939444,
|
| 406 |
+
"grad_norm": 0.5536600351333618,
|
| 407 |
+
"learning_rate": 1.949559724349158e-05,
|
| 408 |
+
"loss": 0.0844,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.2498061848565768,
|
| 413 |
+
"grad_norm": 0.7858330011367798,
|
| 414 |
+
"learning_rate": 1.9447741194486983e-05,
|
| 415 |
+
"loss": 0.0971,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.25411318804375915,
|
| 420 |
+
"grad_norm": 0.7134358882904053,
|
| 421 |
+
"learning_rate": 1.939988514548239e-05,
|
| 422 |
+
"loss": 0.0895,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2584201912309415,
|
| 427 |
+
"grad_norm": 1.947914719581604,
|
| 428 |
+
"learning_rate": 1.9352029096477794e-05,
|
| 429 |
+
"loss": 0.0892,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.26272719441812387,
|
| 434 |
+
"grad_norm": 1.1056923866271973,
|
| 435 |
+
"learning_rate": 1.93041730474732e-05,
|
| 436 |
+
"loss": 0.0859,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.2670341976053062,
|
| 441 |
+
"grad_norm": 1.785502314567566,
|
| 442 |
+
"learning_rate": 1.9256316998468606e-05,
|
| 443 |
+
"loss": 0.0839,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.2713412007924886,
|
| 448 |
+
"grad_norm": 1.1600751876831055,
|
| 449 |
+
"learning_rate": 1.9208460949464013e-05,
|
| 450 |
+
"loss": 0.101,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.27564820397967094,
|
| 455 |
+
"grad_norm": 0.8848490715026855,
|
| 456 |
+
"learning_rate": 1.916060490045942e-05,
|
| 457 |
+
"loss": 0.0933,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2799552071668533,
|
| 462 |
+
"grad_norm": 1.426681637763977,
|
| 463 |
+
"learning_rate": 1.9112748851454824e-05,
|
| 464 |
+
"loss": 0.09,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.28426221035403565,
|
| 469 |
+
"grad_norm": 1.2651540040969849,
|
| 470 |
+
"learning_rate": 1.906489280245023e-05,
|
| 471 |
+
"loss": 0.0813,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.288569213541218,
|
| 476 |
+
"grad_norm": 2.1191368103027344,
|
| 477 |
+
"learning_rate": 1.901703675344564e-05,
|
| 478 |
+
"loss": 0.0883,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.29287621672840036,
|
| 483 |
+
"grad_norm": 3.073676347732544,
|
| 484 |
+
"learning_rate": 1.8969180704441042e-05,
|
| 485 |
+
"loss": 0.0824,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2971832199155827,
|
| 490 |
+
"grad_norm": 1.8992786407470703,
|
| 491 |
+
"learning_rate": 1.892132465543645e-05,
|
| 492 |
+
"loss": 0.0782,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.3014902231027651,
|
| 497 |
+
"grad_norm": 0.8623748421669006,
|
| 498 |
+
"learning_rate": 1.8873468606431853e-05,
|
| 499 |
+
"loss": 0.0856,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.30579722628994743,
|
| 504 |
+
"grad_norm": 1.1716139316558838,
|
| 505 |
+
"learning_rate": 1.882561255742726e-05,
|
| 506 |
+
"loss": 0.0828,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3101042294771298,
|
| 511 |
+
"grad_norm": 1.7309471368789673,
|
| 512 |
+
"learning_rate": 1.8777756508422668e-05,
|
| 513 |
+
"loss": 0.0908,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.31441123266431215,
|
| 518 |
+
"grad_norm": 0.7618270516395569,
|
| 519 |
+
"learning_rate": 1.8729900459418072e-05,
|
| 520 |
+
"loss": 0.0803,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3187182358514945,
|
| 525 |
+
"grad_norm": 2.2501418590545654,
|
| 526 |
+
"learning_rate": 1.868204441041348e-05,
|
| 527 |
+
"loss": 0.0858,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.3230252390386769,
|
| 532 |
+
"grad_norm": 0.5587218403816223,
|
| 533 |
+
"learning_rate": 1.8634188361408883e-05,
|
| 534 |
+
"loss": 0.0774,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.32733224222585927,
|
| 539 |
+
"grad_norm": 1.0532606840133667,
|
| 540 |
+
"learning_rate": 1.858633231240429e-05,
|
| 541 |
+
"loss": 0.1006,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.33163924541304163,
|
| 546 |
+
"grad_norm": 1.4768109321594238,
|
| 547 |
+
"learning_rate": 1.8538476263399698e-05,
|
| 548 |
+
"loss": 0.0711,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.335946248600224,
|
| 553 |
+
"grad_norm": 0.8221687078475952,
|
| 554 |
+
"learning_rate": 1.84906202143951e-05,
|
| 555 |
+
"loss": 0.0767,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.34025325178740634,
|
| 560 |
+
"grad_norm": 1.1903904676437378,
|
| 561 |
+
"learning_rate": 1.844276416539051e-05,
|
| 562 |
+
"loss": 0.0816,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3445602549745887,
|
| 567 |
+
"grad_norm": 2.3019232749938965,
|
| 568 |
+
"learning_rate": 1.8394908116385913e-05,
|
| 569 |
+
"loss": 0.0808,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.34886725816177105,
|
| 574 |
+
"grad_norm": 0.6996669173240662,
|
| 575 |
+
"learning_rate": 1.834705206738132e-05,
|
| 576 |
+
"loss": 0.0765,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3531742613489534,
|
| 581 |
+
"grad_norm": 1.5490134954452515,
|
| 582 |
+
"learning_rate": 1.8299196018376724e-05,
|
| 583 |
+
"loss": 0.0697,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.35748126453613577,
|
| 588 |
+
"grad_norm": 1.420470118522644,
|
| 589 |
+
"learning_rate": 1.825133996937213e-05,
|
| 590 |
+
"loss": 0.0735,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3617882677233181,
|
| 595 |
+
"grad_norm": 0.7981294393539429,
|
| 596 |
+
"learning_rate": 1.8203483920367535e-05,
|
| 597 |
+
"loss": 0.0904,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.3660952709105005,
|
| 602 |
+
"grad_norm": 0.8957176804542542,
|
| 603 |
+
"learning_rate": 1.8155627871362942e-05,
|
| 604 |
+
"loss": 0.0881,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.37040227409768284,
|
| 609 |
+
"grad_norm": 1.6501141786575317,
|
| 610 |
+
"learning_rate": 1.8107771822358346e-05,
|
| 611 |
+
"loss": 0.0875,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3747092772848652,
|
| 616 |
+
"grad_norm": 1.2927387952804565,
|
| 617 |
+
"learning_rate": 1.8059915773353753e-05,
|
| 618 |
+
"loss": 0.0853,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.37901628047204755,
|
| 623 |
+
"grad_norm": 2.036569118499756,
|
| 624 |
+
"learning_rate": 1.801205972434916e-05,
|
| 625 |
+
"loss": 0.0731,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3833232836592299,
|
| 630 |
+
"grad_norm": 0.8174524307250977,
|
| 631 |
+
"learning_rate": 1.7964203675344564e-05,
|
| 632 |
+
"loss": 0.0777,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.38763028684641226,
|
| 637 |
+
"grad_norm": 1.1389156579971313,
|
| 638 |
+
"learning_rate": 1.791634762633997e-05,
|
| 639 |
+
"loss": 0.0877,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3919372900335946,
|
| 644 |
+
"grad_norm": 1.8554282188415527,
|
| 645 |
+
"learning_rate": 1.7868491577335375e-05,
|
| 646 |
+
"loss": 0.088,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.396244293220777,
|
| 651 |
+
"grad_norm": 0.8491562604904175,
|
| 652 |
+
"learning_rate": 1.7820635528330783e-05,
|
| 653 |
+
"loss": 0.079,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.40055129640795933,
|
| 658 |
+
"grad_norm": 1.2037336826324463,
|
| 659 |
+
"learning_rate": 1.7772779479326187e-05,
|
| 660 |
+
"loss": 0.0773,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4048582995951417,
|
| 665 |
+
"grad_norm": 1.5329045057296753,
|
| 666 |
+
"learning_rate": 1.7724923430321594e-05,
|
| 667 |
+
"loss": 0.0685,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.40916530278232405,
|
| 672 |
+
"grad_norm": 2.5743863582611084,
|
| 673 |
+
"learning_rate": 1.7677067381316998e-05,
|
| 674 |
+
"loss": 0.0791,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.4134723059695064,
|
| 679 |
+
"grad_norm": 2.455772876739502,
|
| 680 |
+
"learning_rate": 1.7629211332312405e-05,
|
| 681 |
+
"loss": 0.0733,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.41777930915668876,
|
| 686 |
+
"grad_norm": 0.6685093641281128,
|
| 687 |
+
"learning_rate": 1.758135528330781e-05,
|
| 688 |
+
"loss": 0.0844,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.4220863123438711,
|
| 693 |
+
"grad_norm": 0.3142644464969635,
|
| 694 |
+
"learning_rate": 1.7533499234303216e-05,
|
| 695 |
+
"loss": 0.085,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.4263933155310535,
|
| 700 |
+
"grad_norm": 1.4865537881851196,
|
| 701 |
+
"learning_rate": 1.7485643185298623e-05,
|
| 702 |
+
"loss": 0.0842,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.43070031871823583,
|
| 707 |
+
"grad_norm": 0.6880686283111572,
|
| 708 |
+
"learning_rate": 1.7437787136294027e-05,
|
| 709 |
+
"loss": 0.0863,
|
| 710 |
+
"step": 5000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.4350073219054182,
|
| 714 |
+
"grad_norm": 1.468641757965088,
|
| 715 |
+
"learning_rate": 1.7389931087289434e-05,
|
| 716 |
+
"loss": 0.0665,
|
| 717 |
+
"step": 5050
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.43931432509260054,
|
| 721 |
+
"grad_norm": 0.5643796324729919,
|
| 722 |
+
"learning_rate": 1.7342075038284842e-05,
|
| 723 |
+
"loss": 0.0628,
|
| 724 |
+
"step": 5100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4436213282797829,
|
| 728 |
+
"grad_norm": 1.5360355377197266,
|
| 729 |
+
"learning_rate": 1.7294218989280246e-05,
|
| 730 |
+
"loss": 0.0821,
|
| 731 |
+
"step": 5150
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4479283314669653,
|
| 735 |
+
"grad_norm": 0.4214192032814026,
|
| 736 |
+
"learning_rate": 1.7246362940275653e-05,
|
| 737 |
+
"loss": 0.0819,
|
| 738 |
+
"step": 5200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.45223533465414767,
|
| 742 |
+
"grad_norm": 0.9894843697547913,
|
| 743 |
+
"learning_rate": 1.7198506891271057e-05,
|
| 744 |
+
"loss": 0.0833,
|
| 745 |
+
"step": 5250
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.45654233784133,
|
| 749 |
+
"grad_norm": 0.4610138237476349,
|
| 750 |
+
"learning_rate": 1.7150650842266464e-05,
|
| 751 |
+
"loss": 0.0673,
|
| 752 |
+
"step": 5300
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.4608493410285124,
|
| 756 |
+
"grad_norm": 1.4296882152557373,
|
| 757 |
+
"learning_rate": 1.710279479326187e-05,
|
| 758 |
+
"loss": 0.0835,
|
| 759 |
+
"step": 5350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.46515634421569474,
|
| 763 |
+
"grad_norm": 8.520477294921875,
|
| 764 |
+
"learning_rate": 1.7054938744257275e-05,
|
| 765 |
+
"loss": 0.0728,
|
| 766 |
+
"step": 5400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4694633474028771,
|
| 770 |
+
"grad_norm": 2.569798469543457,
|
| 771 |
+
"learning_rate": 1.7007082695252682e-05,
|
| 772 |
+
"loss": 0.077,
|
| 773 |
+
"step": 5450
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.47377035059005945,
|
| 777 |
+
"grad_norm": 0.4249440133571625,
|
| 778 |
+
"learning_rate": 1.695922664624809e-05,
|
| 779 |
+
"loss": 0.0769,
|
| 780 |
+
"step": 5500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4780773537772418,
|
| 784 |
+
"grad_norm": 0.9137064814567566,
|
| 785 |
+
"learning_rate": 1.6911370597243494e-05,
|
| 786 |
+
"loss": 0.0738,
|
| 787 |
+
"step": 5550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.48238435696442417,
|
| 791 |
+
"grad_norm": 2.170475482940674,
|
| 792 |
+
"learning_rate": 1.68635145482389e-05,
|
| 793 |
+
"loss": 0.0911,
|
| 794 |
+
"step": 5600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4866913601516065,
|
| 798 |
+
"grad_norm": 1.3690396547317505,
|
| 799 |
+
"learning_rate": 1.6815658499234305e-05,
|
| 800 |
+
"loss": 0.0836,
|
| 801 |
+
"step": 5650
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4909983633387889,
|
| 805 |
+
"grad_norm": 0.6001138687133789,
|
| 806 |
+
"learning_rate": 1.6767802450229712e-05,
|
| 807 |
+
"loss": 0.0702,
|
| 808 |
+
"step": 5700
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.49530536652597124,
|
| 812 |
+
"grad_norm": 0.9974215626716614,
|
| 813 |
+
"learning_rate": 1.6719946401225116e-05,
|
| 814 |
+
"loss": 0.0718,
|
| 815 |
+
"step": 5750
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.4996123697131536,
|
| 819 |
+
"grad_norm": 1.320965051651001,
|
| 820 |
+
"learning_rate": 1.6672090352220523e-05,
|
| 821 |
+
"loss": 0.0878,
|
| 822 |
+
"step": 5800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.503919372900336,
|
| 826 |
+
"grad_norm": 3.4302828311920166,
|
| 827 |
+
"learning_rate": 1.6624234303215927e-05,
|
| 828 |
+
"loss": 0.0765,
|
| 829 |
+
"step": 5850
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5082263760875183,
|
| 833 |
+
"grad_norm": 3.066030979156494,
|
| 834 |
+
"learning_rate": 1.6576378254211334e-05,
|
| 835 |
+
"loss": 0.0793,
|
| 836 |
+
"step": 5900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5125333792747007,
|
| 840 |
+
"grad_norm": 0.40252232551574707,
|
| 841 |
+
"learning_rate": 1.6528522205206738e-05,
|
| 842 |
+
"loss": 0.0775,
|
| 843 |
+
"step": 5950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.516840382461883,
|
| 847 |
+
"grad_norm": 0.5411482453346252,
|
| 848 |
+
"learning_rate": 1.6480666156202145e-05,
|
| 849 |
+
"loss": 0.0587,
|
| 850 |
+
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5211473856490654,
|
| 854 |
+
"grad_norm": 1.5473580360412598,
|
| 855 |
+
"learning_rate": 1.6432810107197553e-05,
|
| 856 |
+
"loss": 0.0828,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5254543888362477,
|
| 861 |
+
"grad_norm": 0.5236213207244873,
|
| 862 |
+
"learning_rate": 1.6384954058192956e-05,
|
| 863 |
+
"loss": 0.0834,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5297613920234301,
|
| 868 |
+
"grad_norm": 0.6478111147880554,
|
| 869 |
+
"learning_rate": 1.6337098009188364e-05,
|
| 870 |
+
"loss": 0.0832,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5340683952106124,
|
| 875 |
+
"grad_norm": 0.9006224274635315,
|
| 876 |
+
"learning_rate": 1.6289241960183768e-05,
|
| 877 |
+
"loss": 0.0702,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5383753983977948,
|
| 882 |
+
"grad_norm": 0.797485888004303,
|
| 883 |
+
"learning_rate": 1.6241385911179175e-05,
|
| 884 |
+
"loss": 0.067,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5426824015849772,
|
| 889 |
+
"grad_norm": 1.9563658237457275,
|
| 890 |
+
"learning_rate": 1.619352986217458e-05,
|
| 891 |
+
"loss": 0.0801,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5469894047721595,
|
| 896 |
+
"grad_norm": 0.5427608489990234,
|
| 897 |
+
"learning_rate": 1.6145673813169986e-05,
|
| 898 |
+
"loss": 0.071,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5512964079593419,
|
| 903 |
+
"grad_norm": 0.6721413731575012,
|
| 904 |
+
"learning_rate": 1.609781776416539e-05,
|
| 905 |
+
"loss": 0.0748,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5556034111465242,
|
| 910 |
+
"grad_norm": 0.3382332921028137,
|
| 911 |
+
"learning_rate": 1.6049961715160797e-05,
|
| 912 |
+
"loss": 0.0707,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5599104143337066,
|
| 917 |
+
"grad_norm": 5.356226921081543,
|
| 918 |
+
"learning_rate": 1.60021056661562e-05,
|
| 919 |
+
"loss": 0.0809,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5642174175208889,
|
| 924 |
+
"grad_norm": 9.463122367858887,
|
| 925 |
+
"learning_rate": 1.5954249617151608e-05,
|
| 926 |
+
"loss": 0.0791,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5685244207080713,
|
| 931 |
+
"grad_norm": 0.8620396852493286,
|
| 932 |
+
"learning_rate": 1.5906393568147016e-05,
|
| 933 |
+
"loss": 0.0723,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5728314238952537,
|
| 938 |
+
"grad_norm": 0.8391813039779663,
|
| 939 |
+
"learning_rate": 1.585853751914242e-05,
|
| 940 |
+
"loss": 0.0679,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.577138427082436,
|
| 945 |
+
"grad_norm": 0.43624547123908997,
|
| 946 |
+
"learning_rate": 1.5810681470137827e-05,
|
| 947 |
+
"loss": 0.0621,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5814454302696184,
|
| 952 |
+
"grad_norm": 0.29170680046081543,
|
| 953 |
+
"learning_rate": 1.576282542113323e-05,
|
| 954 |
+
"loss": 0.0779,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5857524334568007,
|
| 959 |
+
"grad_norm": 1.6128978729248047,
|
| 960 |
+
"learning_rate": 1.5714969372128638e-05,
|
| 961 |
+
"loss": 0.0753,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5900594366439831,
|
| 966 |
+
"grad_norm": 0.8161028027534485,
|
| 967 |
+
"learning_rate": 1.5667113323124045e-05,
|
| 968 |
+
"loss": 0.0902,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5943664398311654,
|
| 973 |
+
"grad_norm": 2.1843135356903076,
|
| 974 |
+
"learning_rate": 1.561925727411945e-05,
|
| 975 |
+
"loss": 0.0724,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5986734430183478,
|
| 980 |
+
"grad_norm": 0.6703418493270874,
|
| 981 |
+
"learning_rate": 1.5571401225114856e-05,
|
| 982 |
+
"loss": 0.0767,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.6029804462055302,
|
| 987 |
+
"grad_norm": 1.8306766748428345,
|
| 988 |
+
"learning_rate": 1.5523545176110263e-05,
|
| 989 |
+
"loss": 0.0722,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6072874493927125,
|
| 994 |
+
"grad_norm": 0.22963102161884308,
|
| 995 |
+
"learning_rate": 1.5475689127105667e-05,
|
| 996 |
+
"loss": 0.0718,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6115944525798949,
|
| 1001 |
+
"grad_norm": 0.7969381213188171,
|
| 1002 |
+
"learning_rate": 1.5427833078101075e-05,
|
| 1003 |
+
"loss": 0.076,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.6159014557670772,
|
| 1008 |
+
"grad_norm": 0.7879788875579834,
|
| 1009 |
+
"learning_rate": 1.537997702909648e-05,
|
| 1010 |
+
"loss": 0.0699,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6202084589542596,
|
| 1015 |
+
"grad_norm": 0.2606644332408905,
|
| 1016 |
+
"learning_rate": 1.5332120980091886e-05,
|
| 1017 |
+
"loss": 0.0628,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.6245154621414419,
|
| 1022 |
+
"grad_norm": 1.4626957178115845,
|
| 1023 |
+
"learning_rate": 1.5284264931087293e-05,
|
| 1024 |
+
"loss": 0.0677,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.6288224653286243,
|
| 1029 |
+
"grad_norm": 1.1196939945220947,
|
| 1030 |
+
"learning_rate": 1.5236408882082697e-05,
|
| 1031 |
+
"loss": 0.0786,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.6331294685158066,
|
| 1036 |
+
"grad_norm": 0.7982302904129028,
|
| 1037 |
+
"learning_rate": 1.5188552833078102e-05,
|
| 1038 |
+
"loss": 0.067,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.637436471702989,
|
| 1043 |
+
"grad_norm": 1.4665405750274658,
|
| 1044 |
+
"learning_rate": 1.5140696784073508e-05,
|
| 1045 |
+
"loss": 0.0806,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6417434748901715,
|
| 1050 |
+
"grad_norm": 0.7624828815460205,
|
| 1051 |
+
"learning_rate": 1.5092840735068914e-05,
|
| 1052 |
+
"loss": 0.074,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.6460504780773538,
|
| 1057 |
+
"grad_norm": 0.7437146902084351,
|
| 1058 |
+
"learning_rate": 1.5044984686064319e-05,
|
| 1059 |
+
"loss": 0.0673,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6503574812645362,
|
| 1064 |
+
"grad_norm": 0.5906650424003601,
|
| 1065 |
+
"learning_rate": 1.4997128637059726e-05,
|
| 1066 |
+
"loss": 0.0766,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.6546644844517185,
|
| 1071 |
+
"grad_norm": 0.4946891963481903,
|
| 1072 |
+
"learning_rate": 1.494927258805513e-05,
|
| 1073 |
+
"loss": 0.0668,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6589714876389009,
|
| 1078 |
+
"grad_norm": 0.6105501055717468,
|
| 1079 |
+
"learning_rate": 1.4901416539050538e-05,
|
| 1080 |
+
"loss": 0.0697,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.6632784908260833,
|
| 1085 |
+
"grad_norm": 0.9553045630455017,
|
| 1086 |
+
"learning_rate": 1.4853560490045945e-05,
|
| 1087 |
+
"loss": 0.0726,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6675854940132656,
|
| 1092 |
+
"grad_norm": 0.8546659350395203,
|
| 1093 |
+
"learning_rate": 1.4805704441041349e-05,
|
| 1094 |
+
"loss": 0.0697,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.671892497200448,
|
| 1099 |
+
"grad_norm": 0.3059767484664917,
|
| 1100 |
+
"learning_rate": 1.4757848392036756e-05,
|
| 1101 |
+
"loss": 0.0617,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6761995003876303,
|
| 1106 |
+
"grad_norm": 1.2229968309402466,
|
| 1107 |
+
"learning_rate": 1.470999234303216e-05,
|
| 1108 |
+
"loss": 0.0749,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6805065035748127,
|
| 1113 |
+
"grad_norm": 0.7220912575721741,
|
| 1114 |
+
"learning_rate": 1.4662136294027567e-05,
|
| 1115 |
+
"loss": 0.0714,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.684813506761995,
|
| 1120 |
+
"grad_norm": 1.9133909940719604,
|
| 1121 |
+
"learning_rate": 1.4614280245022971e-05,
|
| 1122 |
+
"loss": 0.0781,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6891205099491774,
|
| 1127 |
+
"grad_norm": 1.536641240119934,
|
| 1128 |
+
"learning_rate": 1.4566424196018378e-05,
|
| 1129 |
+
"loss": 0.0672,
|
| 1130 |
+
"step": 8000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6934275131363598,
|
| 1134 |
+
"grad_norm": 0.33956751227378845,
|
| 1135 |
+
"learning_rate": 1.4518568147013784e-05,
|
| 1136 |
+
"loss": 0.0679,
|
| 1137 |
+
"step": 8050
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6977345163235421,
|
| 1141 |
+
"grad_norm": 2.469947576522827,
|
| 1142 |
+
"learning_rate": 1.447071209800919e-05,
|
| 1143 |
+
"loss": 0.0698,
|
| 1144 |
+
"step": 8100
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7020415195107245,
|
| 1148 |
+
"grad_norm": 2.045753240585327,
|
| 1149 |
+
"learning_rate": 1.4422856049004595e-05,
|
| 1150 |
+
"loss": 0.0626,
|
| 1151 |
+
"step": 8150
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.7063485226979068,
|
| 1155 |
+
"grad_norm": 0.8558171987533569,
|
| 1156 |
+
"learning_rate": 1.4375e-05,
|
| 1157 |
+
"loss": 0.0613,
|
| 1158 |
+
"step": 8200
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.7106555258850892,
|
| 1162 |
+
"grad_norm": 2.619401454925537,
|
| 1163 |
+
"learning_rate": 1.4327143950995408e-05,
|
| 1164 |
+
"loss": 0.0728,
|
| 1165 |
+
"step": 8250
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7149625290722715,
|
| 1169 |
+
"grad_norm": 0.3059772551059723,
|
| 1170 |
+
"learning_rate": 1.4279287901990813e-05,
|
| 1171 |
+
"loss": 0.0662,
|
| 1172 |
+
"step": 8300
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.7192695322594539,
|
| 1176 |
+
"grad_norm": 0.9506771564483643,
|
| 1177 |
+
"learning_rate": 1.4231431852986219e-05,
|
| 1178 |
+
"loss": 0.0638,
|
| 1179 |
+
"step": 8350
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7235765354466362,
|
| 1183 |
+
"grad_norm": 1.543116569519043,
|
| 1184 |
+
"learning_rate": 1.4183575803981624e-05,
|
| 1185 |
+
"loss": 0.0767,
|
| 1186 |
+
"step": 8400
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.7278835386338186,
|
| 1190 |
+
"grad_norm": 1.3135322332382202,
|
| 1191 |
+
"learning_rate": 1.4135719754977032e-05,
|
| 1192 |
+
"loss": 0.066,
|
| 1193 |
+
"step": 8450
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.732190541821001,
|
| 1197 |
+
"grad_norm": 0.6213423013687134,
|
| 1198 |
+
"learning_rate": 1.4087863705972436e-05,
|
| 1199 |
+
"loss": 0.0693,
|
| 1200 |
+
"step": 8500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.7364975450081833,
|
| 1204 |
+
"grad_norm": 2.0644547939300537,
|
| 1205 |
+
"learning_rate": 1.4040007656967843e-05,
|
| 1206 |
+
"loss": 0.066,
|
| 1207 |
+
"step": 8550
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.7408045481953657,
|
| 1211 |
+
"grad_norm": 0.7741810083389282,
|
| 1212 |
+
"learning_rate": 1.3992151607963247e-05,
|
| 1213 |
+
"loss": 0.0758,
|
| 1214 |
+
"step": 8600
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.745111551382548,
|
| 1218 |
+
"grad_norm": 0.6688942909240723,
|
| 1219 |
+
"learning_rate": 1.3944295558958654e-05,
|
| 1220 |
+
"loss": 0.0591,
|
| 1221 |
+
"step": 8650
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.7494185545697304,
|
| 1225 |
+
"grad_norm": 2.8471806049346924,
|
| 1226 |
+
"learning_rate": 1.3896439509954058e-05,
|
| 1227 |
+
"loss": 0.06,
|
| 1228 |
+
"step": 8700
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.7537255577569127,
|
| 1232 |
+
"grad_norm": 1.0602328777313232,
|
| 1233 |
+
"learning_rate": 1.3848583460949465e-05,
|
| 1234 |
+
"loss": 0.0718,
|
| 1235 |
+
"step": 8750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.7580325609440951,
|
| 1239 |
+
"grad_norm": 3.4519808292388916,
|
| 1240 |
+
"learning_rate": 1.3800727411944872e-05,
|
| 1241 |
+
"loss": 0.0803,
|
| 1242 |
+
"step": 8800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7623395641312775,
|
| 1246 |
+
"grad_norm": 1.391143798828125,
|
| 1247 |
+
"learning_rate": 1.3752871362940276e-05,
|
| 1248 |
+
"loss": 0.0686,
|
| 1249 |
+
"step": 8850
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.7666465673184598,
|
| 1253 |
+
"grad_norm": 0.8685784935951233,
|
| 1254 |
+
"learning_rate": 1.3705015313935683e-05,
|
| 1255 |
+
"loss": 0.0702,
|
| 1256 |
+
"step": 8900
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.7709535705056422,
|
| 1260 |
+
"grad_norm": 0.6198963522911072,
|
| 1261 |
+
"learning_rate": 1.3657159264931087e-05,
|
| 1262 |
+
"loss": 0.0636,
|
| 1263 |
+
"step": 8950
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.7752605736928245,
|
| 1267 |
+
"grad_norm": 1.4789685010910034,
|
| 1268 |
+
"learning_rate": 1.3609303215926495e-05,
|
| 1269 |
+
"loss": 0.0717,
|
| 1270 |
+
"step": 9000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.7795675768800069,
|
| 1274 |
+
"grad_norm": 1.204670786857605,
|
| 1275 |
+
"learning_rate": 1.35614471669219e-05,
|
| 1276 |
+
"loss": 0.0623,
|
| 1277 |
+
"step": 9050
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7838745800671892,
|
| 1281 |
+
"grad_norm": 1.0112426280975342,
|
| 1282 |
+
"learning_rate": 1.3513591117917306e-05,
|
| 1283 |
+
"loss": 0.0656,
|
| 1284 |
+
"step": 9100
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7881815832543716,
|
| 1288 |
+
"grad_norm": 1.8575770854949951,
|
| 1289 |
+
"learning_rate": 1.3465735068912711e-05,
|
| 1290 |
+
"loss": 0.0578,
|
| 1291 |
+
"step": 9150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.792488586441554,
|
| 1295 |
+
"grad_norm": 1.1022111177444458,
|
| 1296 |
+
"learning_rate": 1.3417879019908119e-05,
|
| 1297 |
+
"loss": 0.0691,
|
| 1298 |
+
"step": 9200
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7967955896287363,
|
| 1302 |
+
"grad_norm": 0.5931128859519958,
|
| 1303 |
+
"learning_rate": 1.3370022970903522e-05,
|
| 1304 |
+
"loss": 0.0633,
|
| 1305 |
+
"step": 9250
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.8011025928159187,
|
| 1309 |
+
"grad_norm": 1.2253608703613281,
|
| 1310 |
+
"learning_rate": 1.332216692189893e-05,
|
| 1311 |
+
"loss": 0.0702,
|
| 1312 |
+
"step": 9300
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.805409596003101,
|
| 1316 |
+
"grad_norm": 0.7652605175971985,
|
| 1317 |
+
"learning_rate": 1.3274310872894335e-05,
|
| 1318 |
+
"loss": 0.0674,
|
| 1319 |
+
"step": 9350
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.8097165991902834,
|
| 1323 |
+
"grad_norm": 1.5003615617752075,
|
| 1324 |
+
"learning_rate": 1.322645482388974e-05,
|
| 1325 |
+
"loss": 0.0795,
|
| 1326 |
+
"step": 9400
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.8140236023774657,
|
| 1330 |
+
"grad_norm": 1.2461395263671875,
|
| 1331 |
+
"learning_rate": 1.3178598774885148e-05,
|
| 1332 |
+
"loss": 0.0608,
|
| 1333 |
+
"step": 9450
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.8183306055646481,
|
| 1337 |
+
"grad_norm": 0.8731518983840942,
|
| 1338 |
+
"learning_rate": 1.3130742725880552e-05,
|
| 1339 |
+
"loss": 0.068,
|
| 1340 |
+
"step": 9500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.8226376087518305,
|
| 1344 |
+
"grad_norm": 2.1026711463928223,
|
| 1345 |
+
"learning_rate": 1.308288667687596e-05,
|
| 1346 |
+
"loss": 0.073,
|
| 1347 |
+
"step": 9550
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.8269446119390128,
|
| 1351 |
+
"grad_norm": 0.4744667708873749,
|
| 1352 |
+
"learning_rate": 1.3035030627871363e-05,
|
| 1353 |
+
"loss": 0.0669,
|
| 1354 |
+
"step": 9600
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.8312516151261952,
|
| 1358 |
+
"grad_norm": 3.05696702003479,
|
| 1359 |
+
"learning_rate": 1.298717457886677e-05,
|
| 1360 |
+
"loss": 0.0775,
|
| 1361 |
+
"step": 9650
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.8355586183133775,
|
| 1365 |
+
"grad_norm": 1.1643376350402832,
|
| 1366 |
+
"learning_rate": 1.2939318529862174e-05,
|
| 1367 |
+
"loss": 0.0604,
|
| 1368 |
+
"step": 9700
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.8398656215005599,
|
| 1372 |
+
"grad_norm": 0.754551887512207,
|
| 1373 |
+
"learning_rate": 1.2891462480857581e-05,
|
| 1374 |
+
"loss": 0.0574,
|
| 1375 |
+
"step": 9750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.8441726246877422,
|
| 1379 |
+
"grad_norm": 1.8797564506530762,
|
| 1380 |
+
"learning_rate": 1.2843606431852987e-05,
|
| 1381 |
+
"loss": 0.0644,
|
| 1382 |
+
"step": 9800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.8484796278749246,
|
| 1386 |
+
"grad_norm": 0.7417328953742981,
|
| 1387 |
+
"learning_rate": 1.2795750382848393e-05,
|
| 1388 |
+
"loss": 0.0745,
|
| 1389 |
+
"step": 9850
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.852786631062107,
|
| 1393 |
+
"grad_norm": 1.1714173555374146,
|
| 1394 |
+
"learning_rate": 1.27478943338438e-05,
|
| 1395 |
+
"loss": 0.0557,
|
| 1396 |
+
"step": 9900
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.8570936342492893,
|
| 1400 |
+
"grad_norm": 0.8271815776824951,
|
| 1401 |
+
"learning_rate": 1.2700038284839204e-05,
|
| 1402 |
+
"loss": 0.069,
|
| 1403 |
+
"step": 9950
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.8614006374364717,
|
| 1407 |
+
"grad_norm": 0.645411491394043,
|
| 1408 |
+
"learning_rate": 1.2652182235834611e-05,
|
| 1409 |
+
"loss": 0.0665,
|
| 1410 |
+
"step": 10000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.865707640623654,
|
| 1414 |
+
"grad_norm": 0.6957701444625854,
|
| 1415 |
+
"learning_rate": 1.2604326186830017e-05,
|
| 1416 |
+
"loss": 0.0706,
|
| 1417 |
+
"step": 10050
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.8700146438108364,
|
| 1421 |
+
"grad_norm": 1.031860589981079,
|
| 1422 |
+
"learning_rate": 1.2556470137825422e-05,
|
| 1423 |
+
"loss": 0.0631,
|
| 1424 |
+
"step": 10100
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.8743216469980187,
|
| 1428 |
+
"grad_norm": 1.7548658847808838,
|
| 1429 |
+
"learning_rate": 1.2508614088820828e-05,
|
| 1430 |
+
"loss": 0.0661,
|
| 1431 |
+
"step": 10150
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.8786286501852011,
|
| 1435 |
+
"grad_norm": 0.2149202525615692,
|
| 1436 |
+
"learning_rate": 1.2460758039816235e-05,
|
| 1437 |
+
"loss": 0.0627,
|
| 1438 |
+
"step": 10200
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.8829356533723834,
|
| 1442 |
+
"grad_norm": 0.6990727782249451,
|
| 1443 |
+
"learning_rate": 1.2412901990811639e-05,
|
| 1444 |
+
"loss": 0.0633,
|
| 1445 |
+
"step": 10250
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.8872426565595658,
|
| 1449 |
+
"grad_norm": 0.9302994608879089,
|
| 1450 |
+
"learning_rate": 1.2365045941807046e-05,
|
| 1451 |
+
"loss": 0.0565,
|
| 1452 |
+
"step": 10300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.8915496597467482,
|
| 1456 |
+
"grad_norm": 1.272028923034668,
|
| 1457 |
+
"learning_rate": 1.231718989280245e-05,
|
| 1458 |
+
"loss": 0.0712,
|
| 1459 |
+
"step": 10350
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8958566629339306,
|
| 1463 |
+
"grad_norm": 1.5300508737564087,
|
| 1464 |
+
"learning_rate": 1.2269333843797857e-05,
|
| 1465 |
+
"loss": 0.0762,
|
| 1466 |
+
"step": 10400
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.900163666121113,
|
| 1470 |
+
"grad_norm": 1.6238781213760376,
|
| 1471 |
+
"learning_rate": 1.2221477794793264e-05,
|
| 1472 |
+
"loss": 0.0726,
|
| 1473 |
+
"step": 10450
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.9044706693082953,
|
| 1477 |
+
"grad_norm": 0.5441045165061951,
|
| 1478 |
+
"learning_rate": 1.2173621745788668e-05,
|
| 1479 |
+
"loss": 0.0646,
|
| 1480 |
+
"step": 10500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.9087776724954777,
|
| 1484 |
+
"grad_norm": 1.1175705194473267,
|
| 1485 |
+
"learning_rate": 1.2125765696784076e-05,
|
| 1486 |
+
"loss": 0.0713,
|
| 1487 |
+
"step": 10550
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.91308467568266,
|
| 1491 |
+
"grad_norm": 1.7363696098327637,
|
| 1492 |
+
"learning_rate": 1.207790964777948e-05,
|
| 1493 |
+
"loss": 0.0701,
|
| 1494 |
+
"step": 10600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.9173916788698424,
|
| 1498 |
+
"grad_norm": 1.51542067527771,
|
| 1499 |
+
"learning_rate": 1.2030053598774887e-05,
|
| 1500 |
+
"loss": 0.0622,
|
| 1501 |
+
"step": 10650
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.9216986820570248,
|
| 1505 |
+
"grad_norm": 1.324157476425171,
|
| 1506 |
+
"learning_rate": 1.198219754977029e-05,
|
| 1507 |
+
"loss": 0.0723,
|
| 1508 |
+
"step": 10700
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.9260056852442071,
|
| 1512 |
+
"grad_norm": 1.1814820766448975,
|
| 1513 |
+
"learning_rate": 1.1934341500765698e-05,
|
| 1514 |
+
"loss": 0.0759,
|
| 1515 |
+
"step": 10750
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.9303126884313895,
|
| 1519 |
+
"grad_norm": 1.3053069114685059,
|
| 1520 |
+
"learning_rate": 1.1886485451761103e-05,
|
| 1521 |
+
"loss": 0.0753,
|
| 1522 |
+
"step": 10800
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.9346196916185718,
|
| 1526 |
+
"grad_norm": 0.6572118997573853,
|
| 1527 |
+
"learning_rate": 1.1838629402756509e-05,
|
| 1528 |
+
"loss": 0.0644,
|
| 1529 |
+
"step": 10850
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.9389266948057542,
|
| 1533 |
+
"grad_norm": 1.1847835779190063,
|
| 1534 |
+
"learning_rate": 1.1790773353751915e-05,
|
| 1535 |
+
"loss": 0.0667,
|
| 1536 |
+
"step": 10900
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.9432336979929365,
|
| 1540 |
+
"grad_norm": 1.3014558553695679,
|
| 1541 |
+
"learning_rate": 1.1742917304747322e-05,
|
| 1542 |
+
"loss": 0.0712,
|
| 1543 |
+
"step": 10950
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.9475407011801189,
|
| 1547 |
+
"grad_norm": 0.6704654693603516,
|
| 1548 |
+
"learning_rate": 1.1695061255742727e-05,
|
| 1549 |
+
"loss": 0.0612,
|
| 1550 |
+
"step": 11000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.9518477043673013,
|
| 1554 |
+
"grad_norm": 1.0475387573242188,
|
| 1555 |
+
"learning_rate": 1.1647205206738133e-05,
|
| 1556 |
+
"loss": 0.0671,
|
| 1557 |
+
"step": 11050
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.9561547075544836,
|
| 1561 |
+
"grad_norm": 1.2632454633712769,
|
| 1562 |
+
"learning_rate": 1.1599349157733539e-05,
|
| 1563 |
+
"loss": 0.0637,
|
| 1564 |
+
"step": 11100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.960461710741666,
|
| 1568 |
+
"grad_norm": 0.740821361541748,
|
| 1569 |
+
"learning_rate": 1.1551493108728944e-05,
|
| 1570 |
+
"loss": 0.0575,
|
| 1571 |
+
"step": 11150
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.9647687139288483,
|
| 1575 |
+
"grad_norm": 0.3395240008831024,
|
| 1576 |
+
"learning_rate": 1.1503637059724351e-05,
|
| 1577 |
+
"loss": 0.0723,
|
| 1578 |
+
"step": 11200
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.9690757171160307,
|
| 1582 |
+
"grad_norm": 1.7956303358078003,
|
| 1583 |
+
"learning_rate": 1.1455781010719755e-05,
|
| 1584 |
+
"loss": 0.0627,
|
| 1585 |
+
"step": 11250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.973382720303213,
|
| 1589 |
+
"grad_norm": 2.0139009952545166,
|
| 1590 |
+
"learning_rate": 1.1407924961715163e-05,
|
| 1591 |
+
"loss": 0.0592,
|
| 1592 |
+
"step": 11300
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.9776897234903954,
|
| 1596 |
+
"grad_norm": 0.92018723487854,
|
| 1597 |
+
"learning_rate": 1.1360068912710566e-05,
|
| 1598 |
+
"loss": 0.061,
|
| 1599 |
+
"step": 11350
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.9819967266775778,
|
| 1603 |
+
"grad_norm": 0.880361020565033,
|
| 1604 |
+
"learning_rate": 1.1312212863705974e-05,
|
| 1605 |
+
"loss": 0.07,
|
| 1606 |
+
"step": 11400
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.9863037298647601,
|
| 1610 |
+
"grad_norm": 0.6149750351905823,
|
| 1611 |
+
"learning_rate": 1.1264356814701378e-05,
|
| 1612 |
+
"loss": 0.0595,
|
| 1613 |
+
"step": 11450
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.9906107330519425,
|
| 1617 |
+
"grad_norm": 1.544424295425415,
|
| 1618 |
+
"learning_rate": 1.1216500765696785e-05,
|
| 1619 |
+
"loss": 0.0602,
|
| 1620 |
+
"step": 11500
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.9949177362391248,
|
| 1624 |
+
"grad_norm": 1.2716889381408691,
|
| 1625 |
+
"learning_rate": 1.1168644716692192e-05,
|
| 1626 |
+
"loss": 0.0685,
|
| 1627 |
+
"step": 11550
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.9992247394263072,
|
| 1631 |
+
"grad_norm": 1.4920927286148071,
|
| 1632 |
+
"learning_rate": 1.1120788667687596e-05,
|
| 1633 |
+
"loss": 0.0651,
|
| 1634 |
+
"step": 11600
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.0035317426134895,
|
| 1638 |
+
"grad_norm": 0.424301415681839,
|
| 1639 |
+
"learning_rate": 1.1072932618683003e-05,
|
| 1640 |
+
"loss": 0.0563,
|
| 1641 |
+
"step": 11650
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.007838745800672,
|
| 1645 |
+
"grad_norm": 3.4888339042663574,
|
| 1646 |
+
"learning_rate": 1.1025076569678409e-05,
|
| 1647 |
+
"loss": 0.0498,
|
| 1648 |
+
"step": 11700
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.0121457489878543,
|
| 1652 |
+
"grad_norm": 1.8000057935714722,
|
| 1653 |
+
"learning_rate": 1.0977220520673814e-05,
|
| 1654 |
+
"loss": 0.0544,
|
| 1655 |
+
"step": 11750
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.0164527521750366,
|
| 1659 |
+
"grad_norm": 1.6794179677963257,
|
| 1660 |
+
"learning_rate": 1.092936447166922e-05,
|
| 1661 |
+
"loss": 0.0518,
|
| 1662 |
+
"step": 11800
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.020759755362219,
|
| 1666 |
+
"grad_norm": 0.8691530227661133,
|
| 1667 |
+
"learning_rate": 1.0881508422664625e-05,
|
| 1668 |
+
"loss": 0.0492,
|
| 1669 |
+
"step": 11850
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.0250667585494013,
|
| 1673 |
+
"grad_norm": 1.5341356992721558,
|
| 1674 |
+
"learning_rate": 1.0833652373660031e-05,
|
| 1675 |
+
"loss": 0.0548,
|
| 1676 |
+
"step": 11900
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.0293737617365837,
|
| 1680 |
+
"grad_norm": 0.7272191643714905,
|
| 1681 |
+
"learning_rate": 1.0785796324655438e-05,
|
| 1682 |
+
"loss": 0.0477,
|
| 1683 |
+
"step": 11950
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.033680764923766,
|
| 1687 |
+
"grad_norm": 3.297430992126465,
|
| 1688 |
+
"learning_rate": 1.0737940275650842e-05,
|
| 1689 |
+
"loss": 0.0564,
|
| 1690 |
+
"step": 12000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.0379877681109484,
|
| 1694 |
+
"grad_norm": 2.1381115913391113,
|
| 1695 |
+
"learning_rate": 1.069008422664625e-05,
|
| 1696 |
+
"loss": 0.0493,
|
| 1697 |
+
"step": 12050
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.0422947712981308,
|
| 1701 |
+
"grad_norm": 0.35196542739868164,
|
| 1702 |
+
"learning_rate": 1.0642228177641657e-05,
|
| 1703 |
+
"loss": 0.0594,
|
| 1704 |
+
"step": 12100
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.046601774485313,
|
| 1708 |
+
"grad_norm": 0.5407779216766357,
|
| 1709 |
+
"learning_rate": 1.059437212863706e-05,
|
| 1710 |
+
"loss": 0.0423,
|
| 1711 |
+
"step": 12150
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.0509087776724955,
|
| 1715 |
+
"grad_norm": 0.5000036954879761,
|
| 1716 |
+
"learning_rate": 1.0546516079632468e-05,
|
| 1717 |
+
"loss": 0.0578,
|
| 1718 |
+
"step": 12200
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.0552157808596778,
|
| 1722 |
+
"grad_norm": 1.0719070434570312,
|
| 1723 |
+
"learning_rate": 1.0498660030627872e-05,
|
| 1724 |
+
"loss": 0.0558,
|
| 1725 |
+
"step": 12250
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.0595227840468602,
|
| 1729 |
+
"grad_norm": 0.8801513314247131,
|
| 1730 |
+
"learning_rate": 1.0450803981623279e-05,
|
| 1731 |
+
"loss": 0.0499,
|
| 1732 |
+
"step": 12300
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.0638297872340425,
|
| 1736 |
+
"grad_norm": 0.505570650100708,
|
| 1737 |
+
"learning_rate": 1.0402947932618683e-05,
|
| 1738 |
+
"loss": 0.0517,
|
| 1739 |
+
"step": 12350
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.068136790421225,
|
| 1743 |
+
"grad_norm": 0.5933739542961121,
|
| 1744 |
+
"learning_rate": 1.035509188361409e-05,
|
| 1745 |
+
"loss": 0.0538,
|
| 1746 |
+
"step": 12400
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.0724437936084072,
|
| 1750 |
+
"grad_norm": 0.5430397987365723,
|
| 1751 |
+
"learning_rate": 1.0307235834609494e-05,
|
| 1752 |
+
"loss": 0.051,
|
| 1753 |
+
"step": 12450
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.0767507967955896,
|
| 1757 |
+
"grad_norm": 0.7267380952835083,
|
| 1758 |
+
"learning_rate": 1.0259379785604901e-05,
|
| 1759 |
+
"loss": 0.0633,
|
| 1760 |
+
"step": 12500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.081057799982772,
|
| 1764 |
+
"grad_norm": 1.5188019275665283,
|
| 1765 |
+
"learning_rate": 1.0211523736600307e-05,
|
| 1766 |
+
"loss": 0.049,
|
| 1767 |
+
"step": 12550
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.0853648031699543,
|
| 1771 |
+
"grad_norm": 0.8384496569633484,
|
| 1772 |
+
"learning_rate": 1.0163667687595712e-05,
|
| 1773 |
+
"loss": 0.0582,
|
| 1774 |
+
"step": 12600
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.0896718063571367,
|
| 1778 |
+
"grad_norm": 0.9252541065216064,
|
| 1779 |
+
"learning_rate": 1.011581163859112e-05,
|
| 1780 |
+
"loss": 0.0598,
|
| 1781 |
+
"step": 12650
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.093978809544319,
|
| 1785 |
+
"grad_norm": 0.33979302644729614,
|
| 1786 |
+
"learning_rate": 1.0067955589586525e-05,
|
| 1787 |
+
"loss": 0.0568,
|
| 1788 |
+
"step": 12700
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.0982858127315014,
|
| 1792 |
+
"grad_norm": 0.8590192794799805,
|
| 1793 |
+
"learning_rate": 1.002009954058193e-05,
|
| 1794 |
+
"loss": 0.0567,
|
| 1795 |
+
"step": 12750
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.1025928159186837,
|
| 1799 |
+
"grad_norm": 0.8227044343948364,
|
| 1800 |
+
"learning_rate": 9.972243491577336e-06,
|
| 1801 |
+
"loss": 0.0584,
|
| 1802 |
+
"step": 12800
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.106899819105866,
|
| 1806 |
+
"grad_norm": 0.6854674220085144,
|
| 1807 |
+
"learning_rate": 9.924387442572742e-06,
|
| 1808 |
+
"loss": 0.0453,
|
| 1809 |
+
"step": 12850
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.1112068222930485,
|
| 1813 |
+
"grad_norm": 0.178119957447052,
|
| 1814 |
+
"learning_rate": 9.876531393568147e-06,
|
| 1815 |
+
"loss": 0.0557,
|
| 1816 |
+
"step": 12900
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.1155138254802308,
|
| 1820 |
+
"grad_norm": 1.638663411140442,
|
| 1821 |
+
"learning_rate": 9.828675344563555e-06,
|
| 1822 |
+
"loss": 0.0553,
|
| 1823 |
+
"step": 12950
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.1198208286674132,
|
| 1827 |
+
"grad_norm": 0.869343638420105,
|
| 1828 |
+
"learning_rate": 9.78081929555896e-06,
|
| 1829 |
+
"loss": 0.0589,
|
| 1830 |
+
"step": 13000
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.1241278318545955,
|
| 1834 |
+
"grad_norm": 2.4052257537841797,
|
| 1835 |
+
"learning_rate": 9.732963246554366e-06,
|
| 1836 |
+
"loss": 0.0518,
|
| 1837 |
+
"step": 13050
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.1284348350417779,
|
| 1841 |
+
"grad_norm": 0.2610708475112915,
|
| 1842 |
+
"learning_rate": 9.685107197549771e-06,
|
| 1843 |
+
"loss": 0.0505,
|
| 1844 |
+
"step": 13100
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.1327418382289602,
|
| 1848 |
+
"grad_norm": 1.1981760263442993,
|
| 1849 |
+
"learning_rate": 9.637251148545177e-06,
|
| 1850 |
+
"loss": 0.058,
|
| 1851 |
+
"step": 13150
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.1370488414161426,
|
| 1855 |
+
"grad_norm": 0.6214156150817871,
|
| 1856 |
+
"learning_rate": 9.589395099540583e-06,
|
| 1857 |
+
"loss": 0.0701,
|
| 1858 |
+
"step": 13200
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.141355844603325,
|
| 1862 |
+
"grad_norm": 0.22922448813915253,
|
| 1863 |
+
"learning_rate": 9.541539050535988e-06,
|
| 1864 |
+
"loss": 0.0476,
|
| 1865 |
+
"step": 13250
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.1456628477905073,
|
| 1869 |
+
"grad_norm": 0.9147392511367798,
|
| 1870 |
+
"learning_rate": 9.493683001531394e-06,
|
| 1871 |
+
"loss": 0.0528,
|
| 1872 |
+
"step": 13300
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.1499698509776897,
|
| 1876 |
+
"grad_norm": 1.4806290864944458,
|
| 1877 |
+
"learning_rate": 9.4458269525268e-06,
|
| 1878 |
+
"loss": 0.0505,
|
| 1879 |
+
"step": 13350
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.154276854164872,
|
| 1883 |
+
"grad_norm": 1.2948312759399414,
|
| 1884 |
+
"learning_rate": 9.397970903522205e-06,
|
| 1885 |
+
"loss": 0.0425,
|
| 1886 |
+
"step": 13400
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.1585838573520544,
|
| 1890 |
+
"grad_norm": 0.4116344749927521,
|
| 1891 |
+
"learning_rate": 9.350114854517612e-06,
|
| 1892 |
+
"loss": 0.0533,
|
| 1893 |
+
"step": 13450
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.1628908605392367,
|
| 1897 |
+
"grad_norm": 1.7612932920455933,
|
| 1898 |
+
"learning_rate": 9.302258805513018e-06,
|
| 1899 |
+
"loss": 0.0556,
|
| 1900 |
+
"step": 13500
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.167197863726419,
|
| 1904 |
+
"grad_norm": 2.914137363433838,
|
| 1905 |
+
"learning_rate": 9.254402756508423e-06,
|
| 1906 |
+
"loss": 0.055,
|
| 1907 |
+
"step": 13550
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.1715048669136015,
|
| 1911 |
+
"grad_norm": 1.7204225063323975,
|
| 1912 |
+
"learning_rate": 9.206546707503829e-06,
|
| 1913 |
+
"loss": 0.0574,
|
| 1914 |
+
"step": 13600
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.1758118701007838,
|
| 1918 |
+
"grad_norm": 2.408177614212036,
|
| 1919 |
+
"learning_rate": 9.158690658499236e-06,
|
| 1920 |
+
"loss": 0.0641,
|
| 1921 |
+
"step": 13650
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.1801188732879662,
|
| 1925 |
+
"grad_norm": 1.426332950592041,
|
| 1926 |
+
"learning_rate": 9.110834609494642e-06,
|
| 1927 |
+
"loss": 0.052,
|
| 1928 |
+
"step": 13700
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.1844258764751485,
|
| 1932 |
+
"grad_norm": 0.5792996883392334,
|
| 1933 |
+
"learning_rate": 9.062978560490047e-06,
|
| 1934 |
+
"loss": 0.0525,
|
| 1935 |
+
"step": 13750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.1887328796623309,
|
| 1939 |
+
"grad_norm": 2.196568012237549,
|
| 1940 |
+
"learning_rate": 9.015122511485453e-06,
|
| 1941 |
+
"loss": 0.0529,
|
| 1942 |
+
"step": 13800
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.1930398828495132,
|
| 1946 |
+
"grad_norm": 2.5975730419158936,
|
| 1947 |
+
"learning_rate": 8.967266462480858e-06,
|
| 1948 |
+
"loss": 0.0491,
|
| 1949 |
+
"step": 13850
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.1973468860366956,
|
| 1953 |
+
"grad_norm": 1.0551437139511108,
|
| 1954 |
+
"learning_rate": 8.919410413476264e-06,
|
| 1955 |
+
"loss": 0.0566,
|
| 1956 |
+
"step": 13900
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.201653889223878,
|
| 1960 |
+
"grad_norm": 3.027376890182495,
|
| 1961 |
+
"learning_rate": 8.87155436447167e-06,
|
| 1962 |
+
"loss": 0.0511,
|
| 1963 |
+
"step": 13950
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.2059608924110603,
|
| 1967 |
+
"grad_norm": 1.6015963554382324,
|
| 1968 |
+
"learning_rate": 8.823698315467075e-06,
|
| 1969 |
+
"loss": 0.0586,
|
| 1970 |
+
"step": 14000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.2102678955982427,
|
| 1974 |
+
"grad_norm": 0.7658204436302185,
|
| 1975 |
+
"learning_rate": 8.775842266462482e-06,
|
| 1976 |
+
"loss": 0.0506,
|
| 1977 |
+
"step": 14050
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.214574898785425,
|
| 1981 |
+
"grad_norm": 2.3595123291015625,
|
| 1982 |
+
"learning_rate": 8.727986217457888e-06,
|
| 1983 |
+
"loss": 0.0517,
|
| 1984 |
+
"step": 14100
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.2188819019726074,
|
| 1988 |
+
"grad_norm": 0.9073886275291443,
|
| 1989 |
+
"learning_rate": 8.680130168453293e-06,
|
| 1990 |
+
"loss": 0.0474,
|
| 1991 |
+
"step": 14150
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.2231889051597897,
|
| 1995 |
+
"grad_norm": 0.658500611782074,
|
| 1996 |
+
"learning_rate": 8.632274119448699e-06,
|
| 1997 |
+
"loss": 0.0563,
|
| 1998 |
+
"step": 14200
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.227495908346972,
|
| 2002 |
+
"grad_norm": 2.2960684299468994,
|
| 2003 |
+
"learning_rate": 8.584418070444104e-06,
|
| 2004 |
+
"loss": 0.0544,
|
| 2005 |
+
"step": 14250
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.2318029115341544,
|
| 2009 |
+
"grad_norm": 0.9984604120254517,
|
| 2010 |
+
"learning_rate": 8.53656202143951e-06,
|
| 2011 |
+
"loss": 0.049,
|
| 2012 |
+
"step": 14300
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.2361099147213368,
|
| 2016 |
+
"grad_norm": 0.8958185315132141,
|
| 2017 |
+
"learning_rate": 8.488705972434916e-06,
|
| 2018 |
+
"loss": 0.0493,
|
| 2019 |
+
"step": 14350
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.2404169179085192,
|
| 2023 |
+
"grad_norm": 1.542946696281433,
|
| 2024 |
+
"learning_rate": 8.440849923430323e-06,
|
| 2025 |
+
"loss": 0.0524,
|
| 2026 |
+
"step": 14400
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.2447239210957015,
|
| 2030 |
+
"grad_norm": 0.2385903298854828,
|
| 2031 |
+
"learning_rate": 8.392993874425728e-06,
|
| 2032 |
+
"loss": 0.0466,
|
| 2033 |
+
"step": 14450
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.2490309242828839,
|
| 2037 |
+
"grad_norm": 0.9785788655281067,
|
| 2038 |
+
"learning_rate": 8.345137825421134e-06,
|
| 2039 |
+
"loss": 0.0484,
|
| 2040 |
+
"step": 14500
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.2533379274700662,
|
| 2044 |
+
"grad_norm": 2.3022348880767822,
|
| 2045 |
+
"learning_rate": 8.29728177641654e-06,
|
| 2046 |
+
"loss": 0.0471,
|
| 2047 |
+
"step": 14550
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.2576449306572486,
|
| 2051 |
+
"grad_norm": 0.9975636601448059,
|
| 2052 |
+
"learning_rate": 8.249425727411947e-06,
|
| 2053 |
+
"loss": 0.0597,
|
| 2054 |
+
"step": 14600
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.261951933844431,
|
| 2058 |
+
"grad_norm": 1.1821328401565552,
|
| 2059 |
+
"learning_rate": 8.201569678407352e-06,
|
| 2060 |
+
"loss": 0.049,
|
| 2061 |
+
"step": 14650
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.2662589370316133,
|
| 2065 |
+
"grad_norm": 1.6942561864852905,
|
| 2066 |
+
"learning_rate": 8.153713629402758e-06,
|
| 2067 |
+
"loss": 0.0515,
|
| 2068 |
+
"step": 14700
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.2705659402187957,
|
| 2072 |
+
"grad_norm": 1.328933835029602,
|
| 2073 |
+
"learning_rate": 8.105857580398164e-06,
|
| 2074 |
+
"loss": 0.0439,
|
| 2075 |
+
"step": 14750
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.274872943405978,
|
| 2079 |
+
"grad_norm": 1.4722241163253784,
|
| 2080 |
+
"learning_rate": 8.058001531393569e-06,
|
| 2081 |
+
"loss": 0.0436,
|
| 2082 |
+
"step": 14800
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.2791799465931604,
|
| 2086 |
+
"grad_norm": 2.0203914642333984,
|
| 2087 |
+
"learning_rate": 8.010145482388975e-06,
|
| 2088 |
+
"loss": 0.0546,
|
| 2089 |
+
"step": 14850
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.2834869497803427,
|
| 2093 |
+
"grad_norm": 0.9574146866798401,
|
| 2094 |
+
"learning_rate": 7.96228943338438e-06,
|
| 2095 |
+
"loss": 0.0506,
|
| 2096 |
+
"step": 14900
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.287793952967525,
|
| 2100 |
+
"grad_norm": 0.8009830713272095,
|
| 2101 |
+
"learning_rate": 7.914433384379786e-06,
|
| 2102 |
+
"loss": 0.0481,
|
| 2103 |
+
"step": 14950
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.2921009561547074,
|
| 2107 |
+
"grad_norm": 0.20448465645313263,
|
| 2108 |
+
"learning_rate": 7.866577335375191e-06,
|
| 2109 |
+
"loss": 0.0494,
|
| 2110 |
+
"step": 15000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.2964079593418898,
|
| 2114 |
+
"grad_norm": 1.4024789333343506,
|
| 2115 |
+
"learning_rate": 7.818721286370597e-06,
|
| 2116 |
+
"loss": 0.0585,
|
| 2117 |
+
"step": 15050
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.3007149625290721,
|
| 2121 |
+
"grad_norm": 1.0482429265975952,
|
| 2122 |
+
"learning_rate": 7.770865237366003e-06,
|
| 2123 |
+
"loss": 0.0503,
|
| 2124 |
+
"step": 15100
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.3050219657162545,
|
| 2128 |
+
"grad_norm": 1.0705618858337402,
|
| 2129 |
+
"learning_rate": 7.72300918836141e-06,
|
| 2130 |
+
"loss": 0.0512,
|
| 2131 |
+
"step": 15150
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.3093289689034369,
|
| 2135 |
+
"grad_norm": 1.0103789567947388,
|
| 2136 |
+
"learning_rate": 7.675153139356815e-06,
|
| 2137 |
+
"loss": 0.0493,
|
| 2138 |
+
"step": 15200
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.3136359720906192,
|
| 2142 |
+
"grad_norm": 0.5771476030349731,
|
| 2143 |
+
"learning_rate": 7.627297090352222e-06,
|
| 2144 |
+
"loss": 0.0521,
|
| 2145 |
+
"step": 15250
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.3179429752778016,
|
| 2149 |
+
"grad_norm": 2.2042696475982666,
|
| 2150 |
+
"learning_rate": 7.579441041347627e-06,
|
| 2151 |
+
"loss": 0.0505,
|
| 2152 |
+
"step": 15300
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.322249978464984,
|
| 2156 |
+
"grad_norm": 1.3316341638565063,
|
| 2157 |
+
"learning_rate": 7.531584992343033e-06,
|
| 2158 |
+
"loss": 0.0526,
|
| 2159 |
+
"step": 15350
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.3265569816521663,
|
| 2163 |
+
"grad_norm": 0.5309921503067017,
|
| 2164 |
+
"learning_rate": 7.4837289433384385e-06,
|
| 2165 |
+
"loss": 0.0437,
|
| 2166 |
+
"step": 15400
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.3308639848393486,
|
| 2170 |
+
"grad_norm": 2.3327813148498535,
|
| 2171 |
+
"learning_rate": 7.435872894333844e-06,
|
| 2172 |
+
"loss": 0.043,
|
| 2173 |
+
"step": 15450
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.335170988026531,
|
| 2177 |
+
"grad_norm": 1.3027863502502441,
|
| 2178 |
+
"learning_rate": 7.38801684532925e-06,
|
| 2179 |
+
"loss": 0.0497,
|
| 2180 |
+
"step": 15500
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.3394779912137136,
|
| 2184 |
+
"grad_norm": 1.2166827917099,
|
| 2185 |
+
"learning_rate": 7.340160796324656e-06,
|
| 2186 |
+
"loss": 0.0459,
|
| 2187 |
+
"step": 15550
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.343784994400896,
|
| 2191 |
+
"grad_norm": 0.7233597636222839,
|
| 2192 |
+
"learning_rate": 7.2923047473200616e-06,
|
| 2193 |
+
"loss": 0.0604,
|
| 2194 |
+
"step": 15600
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.3480919975880783,
|
| 2198 |
+
"grad_norm": 1.1700698137283325,
|
| 2199 |
+
"learning_rate": 7.244448698315467e-06,
|
| 2200 |
+
"loss": 0.0466,
|
| 2201 |
+
"step": 15650
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.3523990007752607,
|
| 2205 |
+
"grad_norm": 1.931059718132019,
|
| 2206 |
+
"learning_rate": 7.196592649310874e-06,
|
| 2207 |
+
"loss": 0.0516,
|
| 2208 |
+
"step": 15700
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.356706003962443,
|
| 2212 |
+
"grad_norm": 1.038208246231079,
|
| 2213 |
+
"learning_rate": 7.14873660030628e-06,
|
| 2214 |
+
"loss": 0.0556,
|
| 2215 |
+
"step": 15750
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.3610130071496254,
|
| 2219 |
+
"grad_norm": 1.1460036039352417,
|
| 2220 |
+
"learning_rate": 7.1008805513016855e-06,
|
| 2221 |
+
"loss": 0.0493,
|
| 2222 |
+
"step": 15800
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.3653200103368077,
|
| 2226 |
+
"grad_norm": 1.3723373413085938,
|
| 2227 |
+
"learning_rate": 7.053024502297091e-06,
|
| 2228 |
+
"loss": 0.0536,
|
| 2229 |
+
"step": 15850
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.36962701352399,
|
| 2233 |
+
"grad_norm": 1.17483651638031,
|
| 2234 |
+
"learning_rate": 7.005168453292497e-06,
|
| 2235 |
+
"loss": 0.0476,
|
| 2236 |
+
"step": 15900
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.3739340167111724,
|
| 2240 |
+
"grad_norm": 1.125335931777954,
|
| 2241 |
+
"learning_rate": 6.957312404287902e-06,
|
| 2242 |
+
"loss": 0.0628,
|
| 2243 |
+
"step": 15950
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.3782410198983548,
|
| 2247 |
+
"grad_norm": 1.4187146425247192,
|
| 2248 |
+
"learning_rate": 6.909456355283309e-06,
|
| 2249 |
+
"loss": 0.0501,
|
| 2250 |
+
"step": 16000
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.3825480230855371,
|
| 2254 |
+
"grad_norm": 0.822158932685852,
|
| 2255 |
+
"learning_rate": 6.861600306278714e-06,
|
| 2256 |
+
"loss": 0.037,
|
| 2257 |
+
"step": 16050
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.3868550262727195,
|
| 2261 |
+
"grad_norm": 0.38852134346961975,
|
| 2262 |
+
"learning_rate": 6.81374425727412e-06,
|
| 2263 |
+
"loss": 0.0524,
|
| 2264 |
+
"step": 16100
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.3911620294599019,
|
| 2268 |
+
"grad_norm": 0.18604524433612823,
|
| 2269 |
+
"learning_rate": 6.765888208269525e-06,
|
| 2270 |
+
"loss": 0.0554,
|
| 2271 |
+
"step": 16150
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.3954690326470842,
|
| 2275 |
+
"grad_norm": 1.7508134841918945,
|
| 2276 |
+
"learning_rate": 6.718032159264931e-06,
|
| 2277 |
+
"loss": 0.0532,
|
| 2278 |
+
"step": 16200
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.3997760358342666,
|
| 2282 |
+
"grad_norm": 1.52213716506958,
|
| 2283 |
+
"learning_rate": 6.670176110260338e-06,
|
| 2284 |
+
"loss": 0.0475,
|
| 2285 |
+
"step": 16250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.404083039021449,
|
| 2289 |
+
"grad_norm": 1.0467345714569092,
|
| 2290 |
+
"learning_rate": 6.622320061255744e-06,
|
| 2291 |
+
"loss": 0.05,
|
| 2292 |
+
"step": 16300
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.4083900422086313,
|
| 2296 |
+
"grad_norm": 2.5641472339630127,
|
| 2297 |
+
"learning_rate": 6.574464012251149e-06,
|
| 2298 |
+
"loss": 0.0453,
|
| 2299 |
+
"step": 16350
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.4126970453958136,
|
| 2303 |
+
"grad_norm": 1.276836633682251,
|
| 2304 |
+
"learning_rate": 6.526607963246555e-06,
|
| 2305 |
+
"loss": 0.0474,
|
| 2306 |
+
"step": 16400
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.417004048582996,
|
| 2310 |
+
"grad_norm": 1.0303916931152344,
|
| 2311 |
+
"learning_rate": 6.4787519142419604e-06,
|
| 2312 |
+
"loss": 0.0522,
|
| 2313 |
+
"step": 16450
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.4213110517701784,
|
| 2317 |
+
"grad_norm": 0.506725013256073,
|
| 2318 |
+
"learning_rate": 6.430895865237367e-06,
|
| 2319 |
+
"loss": 0.0493,
|
| 2320 |
+
"step": 16500
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.4256180549573607,
|
| 2324 |
+
"grad_norm": 0.3680042624473572,
|
| 2325 |
+
"learning_rate": 6.383039816232772e-06,
|
| 2326 |
+
"loss": 0.0471,
|
| 2327 |
+
"step": 16550
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.429925058144543,
|
| 2331 |
+
"grad_norm": 1.661273717880249,
|
| 2332 |
+
"learning_rate": 6.335183767228178e-06,
|
| 2333 |
+
"loss": 0.047,
|
| 2334 |
+
"step": 16600
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.4342320613317254,
|
| 2338 |
+
"grad_norm": 2.3008716106414795,
|
| 2339 |
+
"learning_rate": 6.2873277182235836e-06,
|
| 2340 |
+
"loss": 0.0469,
|
| 2341 |
+
"step": 16650
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.4385390645189078,
|
| 2345 |
+
"grad_norm": 0.6869375109672546,
|
| 2346 |
+
"learning_rate": 6.239471669218989e-06,
|
| 2347 |
+
"loss": 0.0422,
|
| 2348 |
+
"step": 16700
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.4428460677060901,
|
| 2352 |
+
"grad_norm": 1.4465445280075073,
|
| 2353 |
+
"learning_rate": 6.191615620214395e-06,
|
| 2354 |
+
"loss": 0.0505,
|
| 2355 |
+
"step": 16750
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.4471530708932725,
|
| 2359 |
+
"grad_norm": 0.2986087501049042,
|
| 2360 |
+
"learning_rate": 6.143759571209802e-06,
|
| 2361 |
+
"loss": 0.041,
|
| 2362 |
+
"step": 16800
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.4514600740804549,
|
| 2366 |
+
"grad_norm": 2.3436954021453857,
|
| 2367 |
+
"learning_rate": 6.0959035222052075e-06,
|
| 2368 |
+
"loss": 0.0629,
|
| 2369 |
+
"step": 16850
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.4557670772676372,
|
| 2373 |
+
"grad_norm": 0.6339378356933594,
|
| 2374 |
+
"learning_rate": 6.048047473200613e-06,
|
| 2375 |
+
"loss": 0.0611,
|
| 2376 |
+
"step": 16900
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 1.4600740804548196,
|
| 2380 |
+
"grad_norm": 2.9805867671966553,
|
| 2381 |
+
"learning_rate": 6.0001914241960195e-06,
|
| 2382 |
+
"loss": 0.0465,
|
| 2383 |
+
"step": 16950
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.464381083642002,
|
| 2387 |
+
"grad_norm": 0.9966760277748108,
|
| 2388 |
+
"learning_rate": 5.952335375191425e-06,
|
| 2389 |
+
"loss": 0.0508,
|
| 2390 |
+
"step": 17000
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 1.4686880868291843,
|
| 2394 |
+
"grad_norm": 1.8324909210205078,
|
| 2395 |
+
"learning_rate": 5.904479326186831e-06,
|
| 2396 |
+
"loss": 0.0465,
|
| 2397 |
+
"step": 17050
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 1.4729950900163666,
|
| 2401 |
+
"grad_norm": 1.7495779991149902,
|
| 2402 |
+
"learning_rate": 5.856623277182236e-06,
|
| 2403 |
+
"loss": 0.0571,
|
| 2404 |
+
"step": 17100
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 1.477302093203549,
|
| 2408 |
+
"grad_norm": 0.23090070486068726,
|
| 2409 |
+
"learning_rate": 5.808767228177642e-06,
|
| 2410 |
+
"loss": 0.045,
|
| 2411 |
+
"step": 17150
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.4816090963907314,
|
| 2415 |
+
"grad_norm": 0.6519089341163635,
|
| 2416 |
+
"learning_rate": 5.760911179173047e-06,
|
| 2417 |
+
"loss": 0.044,
|
| 2418 |
+
"step": 17200
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.4859160995779137,
|
| 2422 |
+
"grad_norm": 1.1124998331069946,
|
| 2423 |
+
"learning_rate": 5.713055130168454e-06,
|
| 2424 |
+
"loss": 0.0567,
|
| 2425 |
+
"step": 17250
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 1.490223102765096,
|
| 2429 |
+
"grad_norm": 2.0501909255981445,
|
| 2430 |
+
"learning_rate": 5.665199081163859e-06,
|
| 2431 |
+
"loss": 0.0483,
|
| 2432 |
+
"step": 17300
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 1.4945301059522784,
|
| 2436 |
+
"grad_norm": 0.9483489394187927,
|
| 2437 |
+
"learning_rate": 5.617343032159266e-06,
|
| 2438 |
+
"loss": 0.0567,
|
| 2439 |
+
"step": 17350
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.4988371091394608,
|
| 2443 |
+
"grad_norm": 1.6245462894439697,
|
| 2444 |
+
"learning_rate": 5.569486983154671e-06,
|
| 2445 |
+
"loss": 0.0503,
|
| 2446 |
+
"step": 17400
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.5031441123266431,
|
| 2450 |
+
"grad_norm": 0.4003852605819702,
|
| 2451 |
+
"learning_rate": 5.521630934150078e-06,
|
| 2452 |
+
"loss": 0.0447,
|
| 2453 |
+
"step": 17450
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.5074511155138255,
|
| 2457 |
+
"grad_norm": 1.2670204639434814,
|
| 2458 |
+
"learning_rate": 5.473774885145483e-06,
|
| 2459 |
+
"loss": 0.0591,
|
| 2460 |
+
"step": 17500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.5117581187010078,
|
| 2464 |
+
"grad_norm": 0.9135438203811646,
|
| 2465 |
+
"learning_rate": 5.425918836140889e-06,
|
| 2466 |
+
"loss": 0.0461,
|
| 2467 |
+
"step": 17550
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.5160651218881902,
|
| 2471 |
+
"grad_norm": 1.305522084236145,
|
| 2472 |
+
"learning_rate": 5.378062787136294e-06,
|
| 2473 |
+
"loss": 0.044,
|
| 2474 |
+
"step": 17600
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.5203721250753726,
|
| 2478 |
+
"grad_norm": 0.717606782913208,
|
| 2479 |
+
"learning_rate": 5.3302067381317e-06,
|
| 2480 |
+
"loss": 0.052,
|
| 2481 |
+
"step": 17650
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.524679128262555,
|
| 2485 |
+
"grad_norm": 0.8114219307899475,
|
| 2486 |
+
"learning_rate": 5.2823506891271055e-06,
|
| 2487 |
+
"loss": 0.0524,
|
| 2488 |
+
"step": 17700
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.5289861314497373,
|
| 2492 |
+
"grad_norm": 0.671303391456604,
|
| 2493 |
+
"learning_rate": 5.234494640122512e-06,
|
| 2494 |
+
"loss": 0.0509,
|
| 2495 |
+
"step": 17750
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.5332931346369196,
|
| 2499 |
+
"grad_norm": 1.01195228099823,
|
| 2500 |
+
"learning_rate": 5.1866385911179175e-06,
|
| 2501 |
+
"loss": 0.0416,
|
| 2502 |
+
"step": 17800
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.537600137824102,
|
| 2506 |
+
"grad_norm": 2.579928159713745,
|
| 2507 |
+
"learning_rate": 5.138782542113323e-06,
|
| 2508 |
+
"loss": 0.0472,
|
| 2509 |
+
"step": 17850
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.5419071410112843,
|
| 2513 |
+
"grad_norm": 1.5471606254577637,
|
| 2514 |
+
"learning_rate": 5.0909264931087295e-06,
|
| 2515 |
+
"loss": 0.0439,
|
| 2516 |
+
"step": 17900
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 1.5462141441984667,
|
| 2520 |
+
"grad_norm": 1.0204650163650513,
|
| 2521 |
+
"learning_rate": 5.043070444104136e-06,
|
| 2522 |
+
"loss": 0.056,
|
| 2523 |
+
"step": 17950
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.550521147385649,
|
| 2527 |
+
"grad_norm": 0.8030381798744202,
|
| 2528 |
+
"learning_rate": 4.995214395099541e-06,
|
| 2529 |
+
"loss": 0.037,
|
| 2530 |
+
"step": 18000
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.5548281505728314,
|
| 2534 |
+
"grad_norm": 1.757904052734375,
|
| 2535 |
+
"learning_rate": 4.947358346094947e-06,
|
| 2536 |
+
"loss": 0.0454,
|
| 2537 |
+
"step": 18050
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 1.5591351537600138,
|
| 2541 |
+
"grad_norm": 1.815106749534607,
|
| 2542 |
+
"learning_rate": 4.899502297090353e-06,
|
| 2543 |
+
"loss": 0.036,
|
| 2544 |
+
"step": 18100
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.5634421569471961,
|
| 2548 |
+
"grad_norm": 2.616511821746826,
|
| 2549 |
+
"learning_rate": 4.851646248085758e-06,
|
| 2550 |
+
"loss": 0.0524,
|
| 2551 |
+
"step": 18150
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.5677491601343785,
|
| 2555 |
+
"grad_norm": 0.7136842012405396,
|
| 2556 |
+
"learning_rate": 4.803790199081165e-06,
|
| 2557 |
+
"loss": 0.0481,
|
| 2558 |
+
"step": 18200
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 1.5720561633215608,
|
| 2562 |
+
"grad_norm": 1.5790433883666992,
|
| 2563 |
+
"learning_rate": 4.75593415007657e-06,
|
| 2564 |
+
"loss": 0.0592,
|
| 2565 |
+
"step": 18250
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 1.5763631665087432,
|
| 2569 |
+
"grad_norm": 1.7617017030715942,
|
| 2570 |
+
"learning_rate": 4.7080781010719766e-06,
|
| 2571 |
+
"loss": 0.0457,
|
| 2572 |
+
"step": 18300
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 1.5806701696959256,
|
| 2576 |
+
"grad_norm": 1.7412254810333252,
|
| 2577 |
+
"learning_rate": 4.660222052067382e-06,
|
| 2578 |
+
"loss": 0.0436,
|
| 2579 |
+
"step": 18350
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.584977172883108,
|
| 2583 |
+
"grad_norm": 0.2388194501399994,
|
| 2584 |
+
"learning_rate": 4.612366003062788e-06,
|
| 2585 |
+
"loss": 0.0487,
|
| 2586 |
+
"step": 18400
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.5892841760702903,
|
| 2590 |
+
"grad_norm": 0.7730370163917542,
|
| 2591 |
+
"learning_rate": 4.564509954058193e-06,
|
| 2592 |
+
"loss": 0.0516,
|
| 2593 |
+
"step": 18450
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.5935911792574726,
|
| 2597 |
+
"grad_norm": 0.12291459739208221,
|
| 2598 |
+
"learning_rate": 4.516653905053599e-06,
|
| 2599 |
+
"loss": 0.0439,
|
| 2600 |
+
"step": 18500
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.597898182444655,
|
| 2604 |
+
"grad_norm": 2.391618490219116,
|
| 2605 |
+
"learning_rate": 4.468797856049004e-06,
|
| 2606 |
+
"loss": 0.0373,
|
| 2607 |
+
"step": 18550
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.6022051856318373,
|
| 2611 |
+
"grad_norm": 1.8456435203552246,
|
| 2612 |
+
"learning_rate": 4.420941807044411e-06,
|
| 2613 |
+
"loss": 0.0503,
|
| 2614 |
+
"step": 18600
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.6065121888190197,
|
| 2618 |
+
"grad_norm": 1.629968285560608,
|
| 2619 |
+
"learning_rate": 4.373085758039816e-06,
|
| 2620 |
+
"loss": 0.0544,
|
| 2621 |
+
"step": 18650
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.610819192006202,
|
| 2625 |
+
"grad_norm": 1.3089792728424072,
|
| 2626 |
+
"learning_rate": 4.325229709035223e-06,
|
| 2627 |
+
"loss": 0.0435,
|
| 2628 |
+
"step": 18700
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.6151261951933844,
|
| 2632 |
+
"grad_norm": 0.5841522216796875,
|
| 2633 |
+
"learning_rate": 4.277373660030628e-06,
|
| 2634 |
+
"loss": 0.0491,
|
| 2635 |
+
"step": 18750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.6194331983805668,
|
| 2639 |
+
"grad_norm": 19.473167419433594,
|
| 2640 |
+
"learning_rate": 4.229517611026034e-06,
|
| 2641 |
+
"loss": 0.0537,
|
| 2642 |
+
"step": 18800
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.6237402015677491,
|
| 2646 |
+
"grad_norm": 0.3844253718852997,
|
| 2647 |
+
"learning_rate": 4.1816615620214395e-06,
|
| 2648 |
+
"loss": 0.0431,
|
| 2649 |
+
"step": 18850
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.6280472047549315,
|
| 2653 |
+
"grad_norm": 0.4715471863746643,
|
| 2654 |
+
"learning_rate": 4.133805513016846e-06,
|
| 2655 |
+
"loss": 0.0559,
|
| 2656 |
+
"step": 18900
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.6323542079421138,
|
| 2660 |
+
"grad_norm": 0.3531401455402374,
|
| 2661 |
+
"learning_rate": 4.0859494640122515e-06,
|
| 2662 |
+
"loss": 0.0509,
|
| 2663 |
+
"step": 18950
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 1.6366612111292962,
|
| 2667 |
+
"grad_norm": 2.074488639831543,
|
| 2668 |
+
"learning_rate": 4.038093415007657e-06,
|
| 2669 |
+
"loss": 0.0535,
|
| 2670 |
+
"step": 19000
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 1.6409682143164785,
|
| 2674 |
+
"grad_norm": 1.5356402397155762,
|
| 2675 |
+
"learning_rate": 3.990237366003063e-06,
|
| 2676 |
+
"loss": 0.0499,
|
| 2677 |
+
"step": 19050
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 1.645275217503661,
|
| 2681 |
+
"grad_norm": 1.5428074598312378,
|
| 2682 |
+
"learning_rate": 3.942381316998469e-06,
|
| 2683 |
+
"loss": 0.0479,
|
| 2684 |
+
"step": 19100
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 1.6495822206908433,
|
| 2688 |
+
"grad_norm": 0.3270135223865509,
|
| 2689 |
+
"learning_rate": 3.894525267993875e-06,
|
| 2690 |
+
"loss": 0.0531,
|
| 2691 |
+
"step": 19150
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 1.6538892238780256,
|
| 2695 |
+
"grad_norm": 0.8869958519935608,
|
| 2696 |
+
"learning_rate": 3.846669218989281e-06,
|
| 2697 |
+
"loss": 0.0534,
|
| 2698 |
+
"step": 19200
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.6581962270652082,
|
| 2702 |
+
"grad_norm": 1.6112924814224243,
|
| 2703 |
+
"learning_rate": 3.7988131699846866e-06,
|
| 2704 |
+
"loss": 0.047,
|
| 2705 |
+
"step": 19250
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 1.6625032302523906,
|
| 2709 |
+
"grad_norm": 2.2852418422698975,
|
| 2710 |
+
"learning_rate": 3.750957120980092e-06,
|
| 2711 |
+
"loss": 0.0499,
|
| 2712 |
+
"step": 19300
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 1.666810233439573,
|
| 2716 |
+
"grad_norm": 2.5442960262298584,
|
| 2717 |
+
"learning_rate": 3.7031010719754977e-06,
|
| 2718 |
+
"loss": 0.0376,
|
| 2719 |
+
"step": 19350
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.6711172366267553,
|
| 2723 |
+
"grad_norm": 1.912215232849121,
|
| 2724 |
+
"learning_rate": 3.6552450229709037e-06,
|
| 2725 |
+
"loss": 0.0527,
|
| 2726 |
+
"step": 19400
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 1.6754242398139376,
|
| 2730 |
+
"grad_norm": 0.4197739064693451,
|
| 2731 |
+
"learning_rate": 3.6073889739663097e-06,
|
| 2732 |
+
"loss": 0.0373,
|
| 2733 |
+
"step": 19450
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 1.67973124300112,
|
| 2737 |
+
"grad_norm": 1.5696734189987183,
|
| 2738 |
+
"learning_rate": 3.5595329249617157e-06,
|
| 2739 |
+
"loss": 0.0509,
|
| 2740 |
+
"step": 19500
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 1.6840382461883023,
|
| 2744 |
+
"grad_norm": 4.466480255126953,
|
| 2745 |
+
"learning_rate": 3.5116768759571212e-06,
|
| 2746 |
+
"loss": 0.0462,
|
| 2747 |
+
"step": 19550
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 1.6883452493754847,
|
| 2751 |
+
"grad_norm": 0.4503861963748932,
|
| 2752 |
+
"learning_rate": 3.463820826952527e-06,
|
| 2753 |
+
"loss": 0.0557,
|
| 2754 |
+
"step": 19600
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.692652252562667,
|
| 2758 |
+
"grad_norm": 2.021745443344116,
|
| 2759 |
+
"learning_rate": 3.415964777947933e-06,
|
| 2760 |
+
"loss": 0.0522,
|
| 2761 |
+
"step": 19650
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.6969592557498494,
|
| 2765 |
+
"grad_norm": 0.3884812295436859,
|
| 2766 |
+
"learning_rate": 3.3681087289433388e-06,
|
| 2767 |
+
"loss": 0.0431,
|
| 2768 |
+
"step": 19700
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 1.7012662589370318,
|
| 2772 |
+
"grad_norm": 0.8187980055809021,
|
| 2773 |
+
"learning_rate": 3.3202526799387448e-06,
|
| 2774 |
+
"loss": 0.0562,
|
| 2775 |
+
"step": 19750
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.7055732621242141,
|
| 2779 |
+
"grad_norm": 1.7395086288452148,
|
| 2780 |
+
"learning_rate": 3.2723966309341503e-06,
|
| 2781 |
+
"loss": 0.045,
|
| 2782 |
+
"step": 19800
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 1.7098802653113965,
|
| 2786 |
+
"grad_norm": 1.700365424156189,
|
| 2787 |
+
"learning_rate": 3.224540581929556e-06,
|
| 2788 |
+
"loss": 0.0521,
|
| 2789 |
+
"step": 19850
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.7141872684985788,
|
| 2793 |
+
"grad_norm": 1.0853468179702759,
|
| 2794 |
+
"learning_rate": 3.176684532924962e-06,
|
| 2795 |
+
"loss": 0.0393,
|
| 2796 |
+
"step": 19900
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 1.7184942716857612,
|
| 2800 |
+
"grad_norm": 1.3420748710632324,
|
| 2801 |
+
"learning_rate": 3.1288284839203675e-06,
|
| 2802 |
+
"loss": 0.0406,
|
| 2803 |
+
"step": 19950
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 1.7228012748729435,
|
| 2807 |
+
"grad_norm": 0.8145412802696228,
|
| 2808 |
+
"learning_rate": 3.080972434915774e-06,
|
| 2809 |
+
"loss": 0.0397,
|
| 2810 |
+
"step": 20000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 1.727108278060126,
|
| 2814 |
+
"grad_norm": 0.23563265800476074,
|
| 2815 |
+
"learning_rate": 3.0331163859111794e-06,
|
| 2816 |
+
"loss": 0.0424,
|
| 2817 |
+
"step": 20050
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 1.7314152812473083,
|
| 2821 |
+
"grad_norm": 2.2623884677886963,
|
| 2822 |
+
"learning_rate": 2.9852603369065854e-06,
|
| 2823 |
+
"loss": 0.0395,
|
| 2824 |
+
"step": 20100
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 1.7357222844344906,
|
| 2828 |
+
"grad_norm": 1.604957938194275,
|
| 2829 |
+
"learning_rate": 2.937404287901991e-06,
|
| 2830 |
+
"loss": 0.0511,
|
| 2831 |
+
"step": 20150
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 1.740029287621673,
|
| 2835 |
+
"grad_norm": 2.2091991901397705,
|
| 2836 |
+
"learning_rate": 2.8895482388973966e-06,
|
| 2837 |
+
"loss": 0.0363,
|
| 2838 |
+
"step": 20200
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 1.7443362908088553,
|
| 2842 |
+
"grad_norm": 2.466461181640625,
|
| 2843 |
+
"learning_rate": 2.841692189892803e-06,
|
| 2844 |
+
"loss": 0.0467,
|
| 2845 |
+
"step": 20250
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 1.7486432939960377,
|
| 2849 |
+
"grad_norm": 1.3753108978271484,
|
| 2850 |
+
"learning_rate": 2.7938361408882086e-06,
|
| 2851 |
+
"loss": 0.0399,
|
| 2852 |
+
"step": 20300
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 1.75295029718322,
|
| 2856 |
+
"grad_norm": 0.21829356253147125,
|
| 2857 |
+
"learning_rate": 2.7459800918836145e-06,
|
| 2858 |
+
"loss": 0.0499,
|
| 2859 |
+
"step": 20350
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.7572573003704024,
|
| 2863 |
+
"grad_norm": 1.623775601387024,
|
| 2864 |
+
"learning_rate": 2.69812404287902e-06,
|
| 2865 |
+
"loss": 0.0386,
|
| 2866 |
+
"step": 20400
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.7615643035575848,
|
| 2870 |
+
"grad_norm": 0.31017372012138367,
|
| 2871 |
+
"learning_rate": 2.6502679938744257e-06,
|
| 2872 |
+
"loss": 0.0545,
|
| 2873 |
+
"step": 20450
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 1.765871306744767,
|
| 2877 |
+
"grad_norm": 1.3645857572555542,
|
| 2878 |
+
"learning_rate": 2.6024119448698317e-06,
|
| 2879 |
+
"loss": 0.0544,
|
| 2880 |
+
"step": 20500
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 1.7701783099319495,
|
| 2884 |
+
"grad_norm": 0.5786564350128174,
|
| 2885 |
+
"learning_rate": 2.5545558958652377e-06,
|
| 2886 |
+
"loss": 0.0513,
|
| 2887 |
+
"step": 20550
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 1.7744853131191318,
|
| 2891 |
+
"grad_norm": 1.5446126461029053,
|
| 2892 |
+
"learning_rate": 2.5066998468606436e-06,
|
| 2893 |
+
"loss": 0.051,
|
| 2894 |
+
"step": 20600
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 1.7787923163063142,
|
| 2898 |
+
"grad_norm": 1.536481499671936,
|
| 2899 |
+
"learning_rate": 2.4588437978560492e-06,
|
| 2900 |
+
"loss": 0.0484,
|
| 2901 |
+
"step": 20650
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 1.7830993194934965,
|
| 2905 |
+
"grad_norm": 0.7662395238876343,
|
| 2906 |
+
"learning_rate": 2.4109877488514548e-06,
|
| 2907 |
+
"loss": 0.0427,
|
| 2908 |
+
"step": 20700
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 1.787406322680679,
|
| 2912 |
+
"grad_norm": 0.5149988532066345,
|
| 2913 |
+
"learning_rate": 2.3631316998468608e-06,
|
| 2914 |
+
"loss": 0.0536,
|
| 2915 |
+
"step": 20750
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 1.7917133258678613,
|
| 2919 |
+
"grad_norm": 1.9234181642532349,
|
| 2920 |
+
"learning_rate": 2.3152756508422668e-06,
|
| 2921 |
+
"loss": 0.0318,
|
| 2922 |
+
"step": 20800
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 1.7960203290550436,
|
| 2926 |
+
"grad_norm": 0.9649477005004883,
|
| 2927 |
+
"learning_rate": 2.2674196018376723e-06,
|
| 2928 |
+
"loss": 0.0501,
|
| 2929 |
+
"step": 20850
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 1.800327332242226,
|
| 2933 |
+
"grad_norm": 0.837202787399292,
|
| 2934 |
+
"learning_rate": 2.2195635528330783e-06,
|
| 2935 |
+
"loss": 0.042,
|
| 2936 |
+
"step": 20900
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 1.8046343354294083,
|
| 2940 |
+
"grad_norm": 0.19944478571414948,
|
| 2941 |
+
"learning_rate": 2.171707503828484e-06,
|
| 2942 |
+
"loss": 0.0506,
|
| 2943 |
+
"step": 20950
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 1.8089413386165907,
|
| 2947 |
+
"grad_norm": 1.4293054342269897,
|
| 2948 |
+
"learning_rate": 2.12385145482389e-06,
|
| 2949 |
+
"loss": 0.0411,
|
| 2950 |
+
"step": 21000
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 1.813248341803773,
|
| 2954 |
+
"grad_norm": 1.118740200996399,
|
| 2955 |
+
"learning_rate": 2.075995405819296e-06,
|
| 2956 |
+
"loss": 0.0717,
|
| 2957 |
+
"step": 21050
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 1.8175553449909554,
|
| 2961 |
+
"grad_norm": 2.421658992767334,
|
| 2962 |
+
"learning_rate": 2.0281393568147014e-06,
|
| 2963 |
+
"loss": 0.0468,
|
| 2964 |
+
"step": 21100
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 1.8218623481781377,
|
| 2968 |
+
"grad_norm": 0.853029727935791,
|
| 2969 |
+
"learning_rate": 1.9802833078101074e-06,
|
| 2970 |
+
"loss": 0.0486,
|
| 2971 |
+
"step": 21150
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 1.82616935136532,
|
| 2975 |
+
"grad_norm": 1.8735076189041138,
|
| 2976 |
+
"learning_rate": 1.932427258805513e-06,
|
| 2977 |
+
"loss": 0.05,
|
| 2978 |
+
"step": 21200
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 1.8304763545525025,
|
| 2982 |
+
"grad_norm": 1.977677822113037,
|
| 2983 |
+
"learning_rate": 1.884571209800919e-06,
|
| 2984 |
+
"loss": 0.0535,
|
| 2985 |
+
"step": 21250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 1.8347833577396848,
|
| 2989 |
+
"grad_norm": 2.271840810775757,
|
| 2990 |
+
"learning_rate": 1.836715160796325e-06,
|
| 2991 |
+
"loss": 0.0526,
|
| 2992 |
+
"step": 21300
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 1.8390903609268672,
|
| 2996 |
+
"grad_norm": 2.006540298461914,
|
| 2997 |
+
"learning_rate": 1.7888591117917305e-06,
|
| 2998 |
+
"loss": 0.051,
|
| 2999 |
+
"step": 21350
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 1.8433973641140495,
|
| 3003 |
+
"grad_norm": 1.3626161813735962,
|
| 3004 |
+
"learning_rate": 1.7410030627871363e-06,
|
| 3005 |
+
"loss": 0.0399,
|
| 3006 |
+
"step": 21400
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 1.8477043673012319,
|
| 3010 |
+
"grad_norm": 0.36570730805397034,
|
| 3011 |
+
"learning_rate": 1.6931470137825423e-06,
|
| 3012 |
+
"loss": 0.0471,
|
| 3013 |
+
"step": 21450
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 1.8520113704884142,
|
| 3017 |
+
"grad_norm": 1.7157959938049316,
|
| 3018 |
+
"learning_rate": 1.645290964777948e-06,
|
| 3019 |
+
"loss": 0.043,
|
| 3020 |
+
"step": 21500
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 1.8563183736755966,
|
| 3024 |
+
"grad_norm": 1.2254858016967773,
|
| 3025 |
+
"learning_rate": 1.5974349157733536e-06,
|
| 3026 |
+
"loss": 0.0424,
|
| 3027 |
+
"step": 21550
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 1.860625376862779,
|
| 3031 |
+
"grad_norm": 1.4322336912155151,
|
| 3032 |
+
"learning_rate": 1.5495788667687596e-06,
|
| 3033 |
+
"loss": 0.0501,
|
| 3034 |
+
"step": 21600
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 1.8649323800499613,
|
| 3038 |
+
"grad_norm": 1.4406068325042725,
|
| 3039 |
+
"learning_rate": 1.5017228177641654e-06,
|
| 3040 |
+
"loss": 0.0531,
|
| 3041 |
+
"step": 21650
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 1.8692393832371437,
|
| 3045 |
+
"grad_norm": 2.554696798324585,
|
| 3046 |
+
"learning_rate": 1.4538667687595714e-06,
|
| 3047 |
+
"loss": 0.0484,
|
| 3048 |
+
"step": 21700
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 1.873546386424326,
|
| 3052 |
+
"grad_norm": 0.8713269829750061,
|
| 3053 |
+
"learning_rate": 1.4060107197549772e-06,
|
| 3054 |
+
"loss": 0.046,
|
| 3055 |
+
"step": 21750
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 1.8778533896115084,
|
| 3059 |
+
"grad_norm": 2.0310616493225098,
|
| 3060 |
+
"learning_rate": 1.358154670750383e-06,
|
| 3061 |
+
"loss": 0.05,
|
| 3062 |
+
"step": 21800
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 1.8821603927986907,
|
| 3066 |
+
"grad_norm": 1.8652377128601074,
|
| 3067 |
+
"learning_rate": 1.310298621745789e-06,
|
| 3068 |
+
"loss": 0.0392,
|
| 3069 |
+
"step": 21850
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 1.886467395985873,
|
| 3073 |
+
"grad_norm": 1.5653144121170044,
|
| 3074 |
+
"learning_rate": 1.2624425727411945e-06,
|
| 3075 |
+
"loss": 0.033,
|
| 3076 |
+
"step": 21900
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 1.8907743991730555,
|
| 3080 |
+
"grad_norm": 2.5004944801330566,
|
| 3081 |
+
"learning_rate": 1.2145865237366005e-06,
|
| 3082 |
+
"loss": 0.041,
|
| 3083 |
+
"step": 21950
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 1.8950814023602378,
|
| 3087 |
+
"grad_norm": 1.4836455583572388,
|
| 3088 |
+
"learning_rate": 1.166730474732006e-06,
|
| 3089 |
+
"loss": 0.044,
|
| 3090 |
+
"step": 22000
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 1.8993884055474202,
|
| 3094 |
+
"grad_norm": 1.6919801235198975,
|
| 3095 |
+
"learning_rate": 1.118874425727412e-06,
|
| 3096 |
+
"loss": 0.0545,
|
| 3097 |
+
"step": 22050
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 1.9036954087346025,
|
| 3101 |
+
"grad_norm": 1.8865543603897095,
|
| 3102 |
+
"learning_rate": 1.0710183767228178e-06,
|
| 3103 |
+
"loss": 0.0414,
|
| 3104 |
+
"step": 22100
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 1.9080024119217849,
|
| 3108 |
+
"grad_norm": 0.4198527932167053,
|
| 3109 |
+
"learning_rate": 1.0231623277182236e-06,
|
| 3110 |
+
"loss": 0.0442,
|
| 3111 |
+
"step": 22150
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 1.9123094151089672,
|
| 3115 |
+
"grad_norm": 0.2606310546398163,
|
| 3116 |
+
"learning_rate": 9.753062787136294e-07,
|
| 3117 |
+
"loss": 0.0469,
|
| 3118 |
+
"step": 22200
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 1.9166164182961496,
|
| 3122 |
+
"grad_norm": 0.9288612604141235,
|
| 3123 |
+
"learning_rate": 9.274502297090353e-07,
|
| 3124 |
+
"loss": 0.0512,
|
| 3125 |
+
"step": 22250
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 1.920923421483332,
|
| 3129 |
+
"grad_norm": 1.516979455947876,
|
| 3130 |
+
"learning_rate": 8.795941807044412e-07,
|
| 3131 |
+
"loss": 0.0461,
|
| 3132 |
+
"step": 22300
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 1.9252304246705143,
|
| 3136 |
+
"grad_norm": 1.9783177375793457,
|
| 3137 |
+
"learning_rate": 8.31738131699847e-07,
|
| 3138 |
+
"loss": 0.0432,
|
| 3139 |
+
"step": 22350
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 1.9295374278576967,
|
| 3143 |
+
"grad_norm": 1.2530443668365479,
|
| 3144 |
+
"learning_rate": 7.838820826952527e-07,
|
| 3145 |
+
"loss": 0.0479,
|
| 3146 |
+
"step": 22400
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 1.933844431044879,
|
| 3150 |
+
"grad_norm": 1.5902798175811768,
|
| 3151 |
+
"learning_rate": 7.360260336906586e-07,
|
| 3152 |
+
"loss": 0.0445,
|
| 3153 |
+
"step": 22450
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 1.9381514342320614,
|
| 3157 |
+
"grad_norm": 0.8333576321601868,
|
| 3158 |
+
"learning_rate": 6.881699846860644e-07,
|
| 3159 |
+
"loss": 0.0421,
|
| 3160 |
+
"step": 22500
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 1.9424584374192437,
|
| 3164 |
+
"grad_norm": 1.7701886892318726,
|
| 3165 |
+
"learning_rate": 6.403139356814702e-07,
|
| 3166 |
+
"loss": 0.0462,
|
| 3167 |
+
"step": 22550
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 1.946765440606426,
|
| 3171 |
+
"grad_norm": 1.0668516159057617,
|
| 3172 |
+
"learning_rate": 5.924578866768759e-07,
|
| 3173 |
+
"loss": 0.0486,
|
| 3174 |
+
"step": 22600
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 1.9510724437936084,
|
| 3178 |
+
"grad_norm": 1.6580146551132202,
|
| 3179 |
+
"learning_rate": 5.446018376722818e-07,
|
| 3180 |
+
"loss": 0.061,
|
| 3181 |
+
"step": 22650
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 1.9553794469807908,
|
| 3185 |
+
"grad_norm": 3.7873570919036865,
|
| 3186 |
+
"learning_rate": 4.967457886676876e-07,
|
| 3187 |
+
"loss": 0.043,
|
| 3188 |
+
"step": 22700
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 1.9596864501679732,
|
| 3192 |
+
"grad_norm": 1.558131217956543,
|
| 3193 |
+
"learning_rate": 4.488897396630935e-07,
|
| 3194 |
+
"loss": 0.0575,
|
| 3195 |
+
"step": 22750
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 1.9639934533551555,
|
| 3199 |
+
"grad_norm": 1.4098652601242065,
|
| 3200 |
+
"learning_rate": 4.0103369065849927e-07,
|
| 3201 |
+
"loss": 0.0364,
|
| 3202 |
+
"step": 22800
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 1.9683004565423379,
|
| 3206 |
+
"grad_norm": 1.4595451354980469,
|
| 3207 |
+
"learning_rate": 3.531776416539051e-07,
|
| 3208 |
+
"loss": 0.0387,
|
| 3209 |
+
"step": 22850
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 1.9726074597295202,
|
| 3213 |
+
"grad_norm": 1.091275691986084,
|
| 3214 |
+
"learning_rate": 3.053215926493109e-07,
|
| 3215 |
+
"loss": 0.0459,
|
| 3216 |
+
"step": 22900
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 1.9769144629167026,
|
| 3220 |
+
"grad_norm": 0.16121625900268555,
|
| 3221 |
+
"learning_rate": 2.574655436447167e-07,
|
| 3222 |
+
"loss": 0.0477,
|
| 3223 |
+
"step": 22950
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 1.981221466103885,
|
| 3227 |
+
"grad_norm": 1.069191336631775,
|
| 3228 |
+
"learning_rate": 2.0960949464012254e-07,
|
| 3229 |
+
"loss": 0.0578,
|
| 3230 |
+
"step": 23000
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 1.9855284692910673,
|
| 3234 |
+
"grad_norm": 0.8348867297172546,
|
| 3235 |
+
"learning_rate": 1.6175344563552835e-07,
|
| 3236 |
+
"loss": 0.0403,
|
| 3237 |
+
"step": 23050
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 1.9898354724782497,
|
| 3241 |
+
"grad_norm": 1.325718879699707,
|
| 3242 |
+
"learning_rate": 1.1389739663093415e-07,
|
| 3243 |
+
"loss": 0.0385,
|
| 3244 |
+
"step": 23100
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 1.994142475665432,
|
| 3248 |
+
"grad_norm": 1.107627272605896,
|
| 3249 |
+
"learning_rate": 6.604134762633997e-08,
|
| 3250 |
+
"loss": 0.0456,
|
| 3251 |
+
"step": 23150
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 1.9984494788526144,
|
| 3255 |
+
"grad_norm": 1.173421025276184,
|
| 3256 |
+
"learning_rate": 1.818529862174579e-08,
|
| 3257 |
+
"loss": 0.0407,
|
| 3258 |
+
"step": 23200
|
| 3259 |
+
}
|
| 3260 |
+
],
|
| 3261 |
+
"logging_steps": 50,
|
| 3262 |
+
"max_steps": 23218,
|
| 3263 |
+
"num_input_tokens_seen": 0,
|
| 3264 |
+
"num_train_epochs": 2,
|
| 3265 |
+
"save_steps": 500,
|
| 3266 |
+
"stateful_callbacks": {
|
| 3267 |
+
"TrainerControl": {
|
| 3268 |
+
"args": {
|
| 3269 |
+
"should_epoch_stop": false,
|
| 3270 |
+
"should_evaluate": false,
|
| 3271 |
+
"should_log": false,
|
| 3272 |
+
"should_save": true,
|
| 3273 |
+
"should_training_stop": true
|
| 3274 |
+
},
|
| 3275 |
+
"attributes": {}
|
| 3276 |
+
}
|
| 3277 |
+
},
|
| 3278 |
+
"total_flos": 1.954863372257956e+17,
|
| 3279 |
+
"train_batch_size": 32,
|
| 3280 |
+
"trial_name": null,
|
| 3281 |
+
"trial_params": null
|
| 3282 |
+
}
|
deberta_v3_base/fold_0/checkpoint-23218/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71509012c3fc789653b4cba03dfeee8798cbeec78dff6938dc845564b5de4ca9
|
| 3 |
+
size 5905
|
deberta_v3_base/fold_0/checkpoint-500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
deberta_v3_base/fold_0/checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 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-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"relative_attention": true,
|
| 33 |
+
"share_att_key": true,
|
| 34 |
+
"transformers_version": "4.57.3",
|
| 35 |
+
"type_vocab_size": 0,
|
| 36 |
+
"vocab_size": 128100
|
| 37 |
+
}
|
deberta_v3_base/fold_0/checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3c8826467756e8fa00958ed1d051b9ac8042cc124702479c1175d9ac5db68ee
|
| 3 |
+
size 737719272
|
deberta_v3_base/fold_0/checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9edcaab0a7c50ab60034d20cc9d38001abd5e839da19c42a2c8db26d1d86fa3
|
| 3 |
+
size 1475561675
|
deberta_v3_base/fold_0/checkpoint-500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c62eaf27f174d3c8543f5515608c94bd5936849969acb46b005abe5e35145df
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_0/checkpoint-500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08b7dc1c1a3f4c4461d224cea18198714d352759f5d7820ca0baac0f4c3bcb0
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_0/checkpoint-500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9d91dc6d0845c5c264c0e93475edd1c67a44992432ad87397f12bce99e1bafd
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_0/checkpoint-500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e4ab37ec199f35f0d20d20f412da5b0d0d8e93861578280a64e20015e02237
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_0/checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:928630fbb9c600ad16d223817a01414a90e5c110a138d425381aa18c48a7e710
|
| 3 |
+
size 1465
|
deberta_v3_base/fold_0/checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
deberta_v3_base/fold_0/checkpoint-500/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
deberta_v3_base/fold_0/checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
deberta_v3_base/fold_0/checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": -Infinity,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4204545454545454,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.14204545454545456,
|
| 14 |
+
"grad_norm": 3.234814405441284,
|
| 15 |
+
"learning_rate": 6.933962264150943e-06,
|
| 16 |
+
"loss": 0.4692,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.2840909090909091,
|
| 21 |
+
"grad_norm": 0.06082858890295029,
|
| 22 |
+
"learning_rate": 1.4009433962264152e-05,
|
| 23 |
+
"loss": 0.016,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.42613636363636365,
|
| 28 |
+
"grad_norm": 0.049055397510528564,
|
| 29 |
+
"learning_rate": 1.4321052631578948e-05,
|
| 30 |
+
"loss": 0.0008,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.5681818181818182,
|
| 35 |
+
"grad_norm": 0.01664523407816887,
|
| 36 |
+
"learning_rate": 1.3531578947368422e-05,
|
| 37 |
+
"loss": 0.0004,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.7102272727272727,
|
| 42 |
+
"grad_norm": 0.014110437594354153,
|
| 43 |
+
"learning_rate": 1.2742105263157895e-05,
|
| 44 |
+
"loss": 0.0003,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.8522727272727273,
|
| 49 |
+
"grad_norm": 0.02441984787583351,
|
| 50 |
+
"learning_rate": 1.195263157894737e-05,
|
| 51 |
+
"loss": 0.0002,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.9943181818181818,
|
| 56 |
+
"grad_norm": 0.014556517824530602,
|
| 57 |
+
"learning_rate": 1.1163157894736842e-05,
|
| 58 |
+
"loss": 0.0002,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.0,
|
| 63 |
+
"eval_loss": 9.793722152709961,
|
| 64 |
+
"eval_roc_auc": NaN,
|
| 65 |
+
"eval_runtime": 327.5505,
|
| 66 |
+
"eval_samples_per_second": 868.239,
|
| 67 |
+
"eval_steps_per_second": 3.392,
|
| 68 |
+
"step": 352
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.1363636363636362,
|
| 72 |
+
"grad_norm": 0.006129332818090916,
|
| 73 |
+
"learning_rate": 1.0373684210526317e-05,
|
| 74 |
+
"loss": 0.0001,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.2784090909090908,
|
| 79 |
+
"grad_norm": 0.0053391242399811745,
|
| 80 |
+
"learning_rate": 9.58421052631579e-06,
|
| 81 |
+
"loss": 0.0001,
|
| 82 |
+
"step": 450
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.4204545454545454,
|
| 86 |
+
"grad_norm": 0.004584718961268663,
|
| 87 |
+
"learning_rate": 8.794736842105264e-06,
|
| 88 |
+
"loss": 0.0001,
|
| 89 |
+
"step": 500
|
| 90 |
+
}
|
| 91 |
+
],
|
| 92 |
+
"logging_steps": 50,
|
| 93 |
+
"max_steps": 1056,
|
| 94 |
+
"num_input_tokens_seen": 0,
|
| 95 |
+
"num_train_epochs": 3,
|
| 96 |
+
"save_steps": 500,
|
| 97 |
+
"stateful_callbacks": {
|
| 98 |
+
"EarlyStoppingCallback": {
|
| 99 |
+
"args": {
|
| 100 |
+
"early_stopping_patience": 1,
|
| 101 |
+
"early_stopping_threshold": 0.0
|
| 102 |
+
},
|
| 103 |
+
"attributes": {
|
| 104 |
+
"early_stopping_patience_counter": 0
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
"TrainerControl": {
|
| 108 |
+
"args": {
|
| 109 |
+
"should_epoch_stop": false,
|
| 110 |
+
"should_evaluate": false,
|
| 111 |
+
"should_log": false,
|
| 112 |
+
"should_save": true,
|
| 113 |
+
"should_training_stop": false
|
| 114 |
+
},
|
| 115 |
+
"attributes": {}
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"total_flos": 5.159253121276314e+16,
|
| 119 |
+
"train_batch_size": 128,
|
| 120 |
+
"trial_name": null,
|
| 121 |
+
"trial_params": null
|
| 122 |
+
}
|
deberta_v3_base/fold_0/checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54d713a9b7f7addbb556c6778ecce8aeea6e654064eaea3f3b331cd2450781e3
|
| 3 |
+
size 5905
|
deberta_v3_base/fold_1/best/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
deberta_v3_base/fold_1/best/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 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-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"relative_attention": true,
|
| 33 |
+
"share_att_key": true,
|
| 34 |
+
"transformers_version": "4.57.3",
|
| 35 |
+
"type_vocab_size": 0,
|
| 36 |
+
"vocab_size": 128100
|
| 37 |
+
}
|
deberta_v3_base/fold_1/best/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:886d20583c77187a105f4c9be12ded6e2955e7f82a47c4658e7e6a38a6fd05fd
|
| 3 |
+
size 737719272
|
deberta_v3_base/fold_1/best/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
deberta_v3_base/fold_1/best/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
deberta_v3_base/fold_1/best/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
deberta_v3_base/fold_1/best/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02656a9c4145326138a1eef13c04a1e70616cdec0bb983f9a86b6d64f7f2fee2
|
| 3 |
+
size 5905
|
deberta_v3_base/fold_1/checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
deberta_v3_base/fold_1/checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 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-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"relative_attention": true,
|
| 33 |
+
"share_att_key": true,
|
| 34 |
+
"transformers_version": "4.57.3",
|
| 35 |
+
"type_vocab_size": 0,
|
| 36 |
+
"vocab_size": 128100
|
| 37 |
+
}
|
deberta_v3_base/fold_1/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e8e9f89c746dfa91b59bb9b03f844918c1fe6db497141e0bc59eeb9c9b7f070
|
| 3 |
+
size 737719272
|
deberta_v3_base/fold_1/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0595c93a9d8a686ea995c22ab5a721cb7920298a5b9f85bc3ae324ab2b370c15
|
| 3 |
+
size 1475561675
|
deberta_v3_base/fold_1/checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ef81f8e0483cf2407085621966cc37ad30287be459c2ad5724dfbc05cf8168a
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_1/checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a0db33e417d3dce9cc6a86ae07a59488aeb5d0418d40527ac880e693e7d26b5
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_1/checkpoint-1000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52a738ca1a5d592fc8474385805411cd695d75e67e5f0329b48b933ac427be1f
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_1/checkpoint-1000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58415c5f7f0e34685c252304a64a29a429ffc7fd422c414da6b8181458c5de2d
|
| 3 |
+
size 15429
|
deberta_v3_base/fold_1/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec536822b842cfa420a11d42c3021248862787cf2f0519fdea21308bc8f6a140
|
| 3 |
+
size 1465
|