Upload folder using huggingface_hub
Browse files- README.md +3 -15
- adapter_config.json +7 -10
- adapter_model.bin +2 -2
- adapter_model/adapter_config.json +5 -8
- adapter_model/adapter_model.bin +2 -2
- optimizer.pt +2 -2
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- special_tokens_map.json +4 -22
- tokenizer.json +0 -0
- tokenizer_config.json +7 -28
- trainer_state.json +44 -524
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -12,21 +12,9 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 12 |
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
- llm_int8_has_fp16_weight: False
|
| 14 |
- bnb_4bit_quant_type: nf4
|
| 15 |
-
- bnb_4bit_use_double_quant:
|
| 16 |
-
- bnb_4bit_compute_dtype:
|
| 17 |
-
|
| 18 |
-
The following `bitsandbytes` quantization config was used during training:
|
| 19 |
-
- load_in_8bit: False
|
| 20 |
-
- load_in_4bit: True
|
| 21 |
-
- llm_int8_threshold: 6.0
|
| 22 |
-
- llm_int8_skip_modules: None
|
| 23 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
| 24 |
-
- llm_int8_has_fp16_weight: False
|
| 25 |
-
- bnb_4bit_quant_type: nf4
|
| 26 |
-
- bnb_4bit_use_double_quant: False
|
| 27 |
-
- bnb_4bit_compute_dtype: float16
|
| 28 |
### Framework versions
|
| 29 |
|
| 30 |
-
- PEFT 0.5.0.dev0
|
| 31 |
|
| 32 |
-
- PEFT 0.
|
|
|
|
| 12 |
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
- llm_int8_has_fp16_weight: False
|
| 14 |
- bnb_4bit_quant_type: nf4
|
| 15 |
+
- bnb_4bit_use_double_quant: True
|
| 16 |
+
- bnb_4bit_compute_dtype: float32
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
### Framework versions
|
| 18 |
|
|
|
|
| 19 |
|
| 20 |
+
- PEFT 0.4.0
|
adapter_config.json
CHANGED
|
@@ -1,26 +1,23 @@
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
| 7 |
"init_lora_weights": true,
|
| 8 |
"layers_pattern": null,
|
| 9 |
"layers_to_transform": null,
|
| 10 |
-
"lora_alpha": 16,
|
| 11 |
-
"lora_dropout": 0.
|
| 12 |
"modules_to_save": null,
|
| 13 |
"peft_type": "LORA",
|
| 14 |
"r": 64,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"down_proj",
|
| 22 |
-
"gate_proj",
|
| 23 |
-
"v_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "EleutherAI/pythia-1.4b-deduped",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
| 7 |
"init_lora_weights": true,
|
| 8 |
"layers_pattern": null,
|
| 9 |
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16.0,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
"modules_to_save": null,
|
| 13 |
"peft_type": "LORA",
|
| 14 |
"r": 64,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
+
"query_key_value",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_4h_to_h",
|
| 20 |
+
"dense_h_to_4h"
|
|
|
|
|
|
|
|
|
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c131d7ef0152ba05901fcc4d00eb8d3989c4ab25884d85967b687a68fe837221
|
| 3 |
+
size 201396877
|
adapter_model/adapter_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
@@ -14,13 +14,10 @@
|
|
| 14 |
"r": 64,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"down_proj",
|
| 22 |
-
"gate_proj",
|
| 23 |
-
"v_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "EleutherAI/pythia-1.4b-deduped",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
|
|
| 14 |
"r": 64,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
+
"query_key_value",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_4h_to_h",
|
| 20 |
+
"dense_h_to_4h"
|
|
|
|
|
|
|
|
|
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
adapter_model/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c131d7ef0152ba05901fcc4d00eb8d3989c4ab25884d85967b687a68fe837221
|
| 3 |
+
size 201396877
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0451a20c28f34735ef7dfa777a68b2a3a923bed7fac096edb2ac3b648829c015
|
| 3 |
+
size 2050282373
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d266ddecfade7ae12d89d853bf0985517cf37a6a52c274d08548cfff0d913c51
|
| 3 |
+
size 14511
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4880f3f40e7ab04d8efce4fc909327351c41d3ccafff780222b4189f527a9a0
|
| 3 |
size 627
|
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "</s>",
|
| 17 |
-
"unk_token": {
|
| 18 |
-
"content": "<unk>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": true,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,31 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"normalized": true,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
"clean_up_tokenization_spaces": false,
|
| 11 |
-
"eos_token": {
|
| 12 |
-
"__type": "AddedToken",
|
| 13 |
-
"content": "</s>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": true,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false
|
| 18 |
-
},
|
| 19 |
"model_max_length": 1000000000000000019884624838656,
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"__type": "AddedToken",
|
| 25 |
-
"content": "<unk>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": true,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"padding_side": "right",
|
| 8 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
}
|
trainer_state.json
CHANGED
|
@@ -1,616 +1,136 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"global_step": 200,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate": 2e-05,
|
| 13 |
-
"loss": 0.9985,
|
| 14 |
-
"step": 2
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.0,
|
| 18 |
-
"learning_rate": 2e-05,
|
| 19 |
-
"loss": 0.886,
|
| 20 |
-
"step": 4
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.0,
|
| 24 |
-
"learning_rate": 2e-05,
|
| 25 |
-
"loss": 1.1051,
|
| 26 |
-
"step": 6
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.0,
|
| 30 |
-
"learning_rate": 2e-05,
|
| 31 |
-
"loss": 1.1122,
|
| 32 |
-
"step": 8
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.0,
|
| 36 |
"learning_rate": 2e-05,
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 10
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate": 2e-05,
|
| 43 |
-
"loss": 1.1521,
|
| 44 |
-
"step": 12
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.0,
|
| 48 |
-
"learning_rate": 2e-05,
|
| 49 |
-
"loss": 1.1679,
|
| 50 |
-
"step": 14
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.0,
|
| 54 |
"learning_rate": 2e-05,
|
| 55 |
-
"loss": 1.
|
| 56 |
-
"step": 16
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.0,
|
| 60 |
-
"learning_rate": 2e-05,
|
| 61 |
-
"loss": 1.1099,
|
| 62 |
-
"step": 18
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.0,
|
| 66 |
-
"learning_rate": 2e-05,
|
| 67 |
-
"loss": 1.1247,
|
| 68 |
"step": 20
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0.
|
| 72 |
-
"learning_rate": 2e-05,
|
| 73 |
-
"loss": 1.2112,
|
| 74 |
-
"step": 22
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.0,
|
| 78 |
"learning_rate": 2e-05,
|
| 79 |
-
"loss": 1.
|
| 80 |
-
"step": 24
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.0,
|
| 84 |
-
"learning_rate": 2e-05,
|
| 85 |
-
"loss": 1.1411,
|
| 86 |
-
"step": 26
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.0,
|
| 90 |
-
"learning_rate": 2e-05,
|
| 91 |
-
"loss": 1.3501,
|
| 92 |
-
"step": 28
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.0,
|
| 96 |
-
"learning_rate": 2e-05,
|
| 97 |
-
"loss": 1.1767,
|
| 98 |
"step": 30
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate": 2e-05,
|
| 103 |
-
"loss": 1.2272,
|
| 104 |
-
"step": 32
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 0.0,
|
| 108 |
-
"learning_rate": 2e-05,
|
| 109 |
-
"loss": 1.2486,
|
| 110 |
-
"step": 34
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 0.0,
|
| 114 |
-
"learning_rate": 2e-05,
|
| 115 |
-
"loss": 1.2727,
|
| 116 |
-
"step": 36
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.0,
|
| 120 |
"learning_rate": 2e-05,
|
| 121 |
-
"loss":
|
| 122 |
-
"step": 38
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.0,
|
| 126 |
-
"learning_rate": 2e-05,
|
| 127 |
-
"loss": 1.333,
|
| 128 |
"step": 40
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
"learning_rate": 2e-05,
|
| 133 |
-
"loss":
|
| 134 |
-
"step": 42
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 0.01,
|
| 138 |
-
"learning_rate": 2e-05,
|
| 139 |
-
"loss": 1.3425,
|
| 140 |
-
"step": 44
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 0.01,
|
| 144 |
-
"learning_rate": 2e-05,
|
| 145 |
-
"loss": 1.3959,
|
| 146 |
-
"step": 46
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.01,
|
| 150 |
-
"learning_rate": 2e-05,
|
| 151 |
-
"loss": 1.3078,
|
| 152 |
-
"step": 48
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 0.01,
|
| 156 |
-
"learning_rate": 2e-05,
|
| 157 |
-
"loss": 2.4367,
|
| 158 |
"step": 50
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 0.
|
| 162 |
"learning_rate": 2e-05,
|
| 163 |
-
"loss":
|
| 164 |
-
"step": 52
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.01,
|
| 168 |
-
"learning_rate": 2e-05,
|
| 169 |
-
"loss": 0.7958,
|
| 170 |
-
"step": 54
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.01,
|
| 174 |
-
"learning_rate": 2e-05,
|
| 175 |
-
"loss": 0.9266,
|
| 176 |
-
"step": 56
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.01,
|
| 180 |
-
"learning_rate": 2e-05,
|
| 181 |
-
"loss": 0.9467,
|
| 182 |
-
"step": 58
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 0.01,
|
| 186 |
-
"learning_rate": 2e-05,
|
| 187 |
-
"loss": 0.9492,
|
| 188 |
"step": 60
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch": 0.
|
| 192 |
-
"learning_rate": 2e-05,
|
| 193 |
-
"loss": 1.0022,
|
| 194 |
-
"step": 62
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 0.01,
|
| 198 |
-
"learning_rate": 2e-05,
|
| 199 |
-
"loss": 1.0071,
|
| 200 |
-
"step": 64
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.01,
|
| 204 |
-
"learning_rate": 2e-05,
|
| 205 |
-
"loss": 0.8606,
|
| 206 |
-
"step": 66
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.01,
|
| 210 |
-
"learning_rate": 2e-05,
|
| 211 |
-
"loss": 0.9849,
|
| 212 |
-
"step": 68
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 0.01,
|
| 216 |
"learning_rate": 2e-05,
|
| 217 |
-
"loss": 1.
|
| 218 |
"step": 70
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 0.
|
| 222 |
"learning_rate": 2e-05,
|
| 223 |
-
"loss":
|
| 224 |
-
"step": 72
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 0.01,
|
| 228 |
-
"learning_rate": 2e-05,
|
| 229 |
-
"loss": 0.9118,
|
| 230 |
-
"step": 74
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 0.01,
|
| 234 |
-
"learning_rate": 2e-05,
|
| 235 |
-
"loss": 1.0096,
|
| 236 |
-
"step": 76
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 0.01,
|
| 240 |
-
"learning_rate": 2e-05,
|
| 241 |
-
"loss": 0.9651,
|
| 242 |
-
"step": 78
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.01,
|
| 246 |
-
"learning_rate": 2e-05,
|
| 247 |
-
"loss": 1.0071,
|
| 248 |
"step": 80
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 0.
|
| 252 |
-
"learning_rate": 2e-05,
|
| 253 |
-
"loss": 0.9272,
|
| 254 |
-
"step": 82
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 0.01,
|
| 258 |
-
"learning_rate": 2e-05,
|
| 259 |
-
"loss": 0.9486,
|
| 260 |
-
"step": 84
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 0.01,
|
| 264 |
-
"learning_rate": 2e-05,
|
| 265 |
-
"loss": 1.0818,
|
| 266 |
-
"step": 86
|
| 267 |
-
},
|
| 268 |
-
{
|
| 269 |
-
"epoch": 0.01,
|
| 270 |
"learning_rate": 2e-05,
|
| 271 |
-
"loss":
|
| 272 |
-
"step": 88
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 0.01,
|
| 276 |
-
"learning_rate": 2e-05,
|
| 277 |
-
"loss": 1.0475,
|
| 278 |
"step": 90
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 0.
|
| 282 |
-
"learning_rate": 2e-05,
|
| 283 |
-
"loss": 1.1217,
|
| 284 |
-
"step": 92
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.01,
|
| 288 |
-
"learning_rate": 2e-05,
|
| 289 |
-
"loss": 1.0328,
|
| 290 |
-
"step": 94
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.01,
|
| 294 |
"learning_rate": 2e-05,
|
| 295 |
-
"loss":
|
| 296 |
-
"step": 96
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.01,
|
| 300 |
-
"learning_rate": 2e-05,
|
| 301 |
-
"loss": 0.9313,
|
| 302 |
-
"step": 98
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 0.01,
|
| 306 |
-
"learning_rate": 2e-05,
|
| 307 |
-
"loss": 1.9119,
|
| 308 |
"step": 100
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch": 0.
|
| 312 |
-
"learning_rate": 2e-05,
|
| 313 |
-
"loss": 0.7919,
|
| 314 |
-
"step": 102
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.01,
|
| 318 |
"learning_rate": 2e-05,
|
| 319 |
-
"loss":
|
| 320 |
-
"step": 104
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.01,
|
| 324 |
-
"learning_rate": 2e-05,
|
| 325 |
-
"loss": 0.8743,
|
| 326 |
-
"step": 106
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.01,
|
| 330 |
-
"learning_rate": 2e-05,
|
| 331 |
-
"loss": 0.8572,
|
| 332 |
-
"step": 108
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.01,
|
| 336 |
-
"learning_rate": 2e-05,
|
| 337 |
-
"loss": 0.8919,
|
| 338 |
"step": 110
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
"learning_rate": 2e-05,
|
| 343 |
-
"loss":
|
| 344 |
-
"step": 112
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 0.01,
|
| 348 |
-
"learning_rate": 2e-05,
|
| 349 |
-
"loss": 0.8218,
|
| 350 |
-
"step": 114
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 0.01,
|
| 354 |
-
"learning_rate": 2e-05,
|
| 355 |
-
"loss": 0.8647,
|
| 356 |
-
"step": 116
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 0.01,
|
| 360 |
-
"learning_rate": 2e-05,
|
| 361 |
-
"loss": 0.8727,
|
| 362 |
-
"step": 118
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 0.01,
|
| 366 |
-
"learning_rate": 2e-05,
|
| 367 |
-
"loss": 0.8096,
|
| 368 |
"step": 120
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch": 0.
|
| 372 |
-
"learning_rate": 2e-05,
|
| 373 |
-
"loss": 0.9242,
|
| 374 |
-
"step": 122
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.02,
|
| 378 |
-
"learning_rate": 2e-05,
|
| 379 |
-
"loss": 0.7764,
|
| 380 |
-
"step": 124
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 0.02,
|
| 384 |
"learning_rate": 2e-05,
|
| 385 |
-
"loss":
|
| 386 |
-
"step": 126
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 0.02,
|
| 390 |
-
"learning_rate": 2e-05,
|
| 391 |
-
"loss": 0.7131,
|
| 392 |
-
"step": 128
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 0.02,
|
| 396 |
-
"learning_rate": 2e-05,
|
| 397 |
-
"loss": 0.8053,
|
| 398 |
"step": 130
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch": 0.
|
| 402 |
-
"learning_rate": 2e-05,
|
| 403 |
-
"loss": 0.8017,
|
| 404 |
-
"step": 132
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.02,
|
| 408 |
-
"learning_rate": 2e-05,
|
| 409 |
-
"loss": 0.8523,
|
| 410 |
-
"step": 134
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.02,
|
| 414 |
-
"learning_rate": 2e-05,
|
| 415 |
-
"loss": 0.8351,
|
| 416 |
-
"step": 136
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 0.02,
|
| 420 |
-
"learning_rate": 2e-05,
|
| 421 |
-
"loss": 0.7854,
|
| 422 |
-
"step": 138
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.02,
|
| 426 |
"learning_rate": 2e-05,
|
| 427 |
-
"loss":
|
| 428 |
"step": 140
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch": 0.
|
| 432 |
-
"learning_rate": 2e-05,
|
| 433 |
-
"loss": 0.8467,
|
| 434 |
-
"step": 142
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 0.02,
|
| 438 |
-
"learning_rate": 2e-05,
|
| 439 |
-
"loss": 0.8095,
|
| 440 |
-
"step": 144
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 0.02,
|
| 444 |
"learning_rate": 2e-05,
|
| 445 |
-
"loss":
|
| 446 |
-
"step": 146
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 0.02,
|
| 450 |
-
"learning_rate": 2e-05,
|
| 451 |
-
"loss": 0.9329,
|
| 452 |
-
"step": 148
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 0.02,
|
| 456 |
-
"learning_rate": 2e-05,
|
| 457 |
-
"loss": 1.4044,
|
| 458 |
"step": 150
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch": 0.
|
| 462 |
-
"learning_rate": 2e-05,
|
| 463 |
-
"loss": 0.6767,
|
| 464 |
-
"step": 152
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 0.02,
|
| 468 |
-
"learning_rate": 2e-05,
|
| 469 |
-
"loss": 0.761,
|
| 470 |
-
"step": 154
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 0.02,
|
| 474 |
-
"learning_rate": 2e-05,
|
| 475 |
-
"loss": 0.792,
|
| 476 |
-
"step": 156
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 0.02,
|
| 480 |
-
"learning_rate": 2e-05,
|
| 481 |
-
"loss": 0.786,
|
| 482 |
-
"step": 158
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.02,
|
| 486 |
"learning_rate": 2e-05,
|
| 487 |
-
"loss":
|
| 488 |
"step": 160
|
| 489 |
},
|
| 490 |
{
|
| 491 |
-
"epoch": 0.
|
| 492 |
-
"learning_rate": 2e-05,
|
| 493 |
-
"loss": 0.8232,
|
| 494 |
-
"step": 162
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.02,
|
| 498 |
-
"learning_rate": 2e-05,
|
| 499 |
-
"loss": 0.755,
|
| 500 |
-
"step": 164
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.02,
|
| 504 |
"learning_rate": 2e-05,
|
| 505 |
-
"loss":
|
| 506 |
-
"step": 166
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.02,
|
| 510 |
-
"learning_rate": 2e-05,
|
| 511 |
-
"loss": 0.8464,
|
| 512 |
-
"step": 168
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 0.02,
|
| 516 |
-
"learning_rate": 2e-05,
|
| 517 |
-
"loss": 0.8536,
|
| 518 |
"step": 170
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch": 0.
|
| 522 |
-
"learning_rate": 2e-05,
|
| 523 |
-
"loss": 0.7742,
|
| 524 |
-
"step": 172
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 0.02,
|
| 528 |
-
"learning_rate": 2e-05,
|
| 529 |
-
"loss": 0.804,
|
| 530 |
-
"step": 174
|
| 531 |
-
},
|
| 532 |
-
{
|
| 533 |
-
"epoch": 0.02,
|
| 534 |
-
"learning_rate": 2e-05,
|
| 535 |
-
"loss": 0.8144,
|
| 536 |
-
"step": 176
|
| 537 |
-
},
|
| 538 |
-
{
|
| 539 |
-
"epoch": 0.02,
|
| 540 |
-
"learning_rate": 2e-05,
|
| 541 |
-
"loss": 0.729,
|
| 542 |
-
"step": 178
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 0.02,
|
| 546 |
"learning_rate": 2e-05,
|
| 547 |
-
"loss":
|
| 548 |
"step": 180
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch": 0.
|
| 552 |
-
"learning_rate": 2e-05,
|
| 553 |
-
"loss": 0.7174,
|
| 554 |
-
"step": 182
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 0.02,
|
| 558 |
-
"learning_rate": 2e-05,
|
| 559 |
-
"loss": 0.7451,
|
| 560 |
-
"step": 184
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 0.02,
|
| 564 |
-
"learning_rate": 2e-05,
|
| 565 |
-
"loss": 0.8926,
|
| 566 |
-
"step": 186
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.02,
|
| 570 |
-
"learning_rate": 2e-05,
|
| 571 |
-
"loss": 0.8575,
|
| 572 |
-
"step": 188
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 0.02,
|
| 576 |
"learning_rate": 2e-05,
|
| 577 |
-
"loss":
|
| 578 |
"step": 190
|
| 579 |
},
|
| 580 |
{
|
| 581 |
-
"epoch": 0.
|
| 582 |
-
"learning_rate": 2e-05,
|
| 583 |
-
"loss": 0.7664,
|
| 584 |
-
"step": 192
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 0.02,
|
| 588 |
-
"learning_rate": 2e-05,
|
| 589 |
-
"loss": 0.8667,
|
| 590 |
-
"step": 194
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 0.02,
|
| 594 |
-
"learning_rate": 2e-05,
|
| 595 |
-
"loss": 0.8064,
|
| 596 |
-
"step": 196
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 0.02,
|
| 600 |
-
"learning_rate": 2e-05,
|
| 601 |
-
"loss": 0.8116,
|
| 602 |
-
"step": 198
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 0.02,
|
| 606 |
"learning_rate": 2e-05,
|
| 607 |
-
"loss":
|
| 608 |
"step": 200
|
| 609 |
}
|
| 610 |
],
|
| 611 |
-
"max_steps":
|
| 612 |
-
"num_train_epochs":
|
| 613 |
-
"total_flos":
|
| 614 |
"trial_name": null,
|
| 615 |
"trial_params": null
|
| 616 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.36272953978689637,
|
| 5 |
"global_step": 200,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"learning_rate": 2e-05,
|
| 13 |
+
"loss": 1.9524,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.04,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 1.9249,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.05,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"learning_rate": 2e-05,
|
| 25 |
+
"loss": 1.9685,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.07,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"learning_rate": 2e-05,
|
| 31 |
+
"loss": 2.1624,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.09,
|
| 36 |
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 2.3455,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
"learning_rate": 2e-05,
|
| 43 |
+
"loss": 1.7288,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.13,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
"learning_rate": 2e-05,
|
| 49 |
+
"loss": 1.712,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.15,
|
| 54 |
"learning_rate": 2e-05,
|
| 55 |
+
"loss": 1.8443,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.16,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"learning_rate": 2e-05,
|
| 61 |
+
"loss": 1.9731,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.18,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
"learning_rate": 2e-05,
|
| 67 |
+
"loss": 2.1967,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"learning_rate": 2e-05,
|
| 73 |
+
"loss": 1.6612,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.22,
|
| 78 |
"learning_rate": 2e-05,
|
| 79 |
+
"loss": 1.6775,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.24,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
"learning_rate": 2e-05,
|
| 85 |
+
"loss": 1.7389,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.25,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
"learning_rate": 2e-05,
|
| 91 |
+
"loss": 1.9169,
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.27,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
"learning_rate": 2e-05,
|
| 97 |
+
"loss": 2.2075,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.29,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
"learning_rate": 2e-05,
|
| 103 |
+
"loss": 1.6245,
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.31,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
"learning_rate": 2e-05,
|
| 109 |
+
"loss": 1.6433,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
"step": 170
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.33,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
"learning_rate": 2e-05,
|
| 115 |
+
"loss": 1.7877,
|
| 116 |
"step": 180
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.34,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
"learning_rate": 2e-05,
|
| 121 |
+
"loss": 1.9041,
|
| 122 |
"step": 190
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.36,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
"learning_rate": 2e-05,
|
| 127 |
+
"loss": 2.1649,
|
| 128 |
"step": 200
|
| 129 |
}
|
| 130 |
],
|
| 131 |
+
"max_steps": 1875,
|
| 132 |
+
"num_train_epochs": 4,
|
| 133 |
+
"total_flos": 4967090265784320.0,
|
| 134 |
"trial_name": null,
|
| 135 |
"trial_params": null
|
| 136 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:643cd8215538899410f2288daee01465ee05e777a4971bf0fec462ea7d279181
|
| 3 |
+
size 5691
|