ramdhanfirdaus commited on
Commit
ba44396
1 Parent(s): d0e2f7d

Training in progress, step 1100, checkpoint

Browse files
last-checkpoint/README.md CHANGED
@@ -201,18 +201,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
201
  ## Training procedure
202
 
203
 
204
- The following `bitsandbytes` quantization config was used during training:
205
- - quant_method: bitsandbytes
206
- - load_in_8bit: False
207
- - load_in_4bit: True
208
- - llm_int8_threshold: 6.0
209
- - llm_int8_skip_modules: None
210
- - llm_int8_enable_fp32_cpu_offload: False
211
- - llm_int8_has_fp16_weight: False
212
- - bnb_4bit_quant_type: nf4
213
- - bnb_4bit_use_double_quant: True
214
- - bnb_4bit_compute_dtype: float16
215
-
216
  ### Framework versions
217
 
218
 
 
201
  ## Training procedure
202
 
203
 
 
 
 
 
 
 
 
 
 
 
 
 
204
  ### Framework versions
205
 
206
 
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f43f1a6738f983616ef9181d252b9c12dd97bc40630e3faed7808619f6f0274
3
  size 50349441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754e6d0c8b95b78534629a453335fe1dc85084eeed008ac125be58b33ee35367
3
  size 50349441
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eba013c6a23ae64f89bf510557c06c2a3eb39e5a9106660abb711cded9be9dda
3
- size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab13fd93fb68dddc6c3824e90e38d5ae241adf08342c0e417e20c8a5f3025b37
3
+ size 100691721
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:367394aed610ff7068eaf27da3eb89a6cd4769f26c2abeadffb65a7a6d3952cd
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4887eda634f542d0c8496ee30ab1130b0b9a4766dc9d31a2130fdb8d2444505
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
3
  size 627
last-checkpoint/special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
  "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
last-checkpoint/tokenizer_config.json CHANGED
@@ -13,8 +13,12 @@
13
  "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
 
16
  "model_max_length": 1024,
17
  "pad_token": "<|endoftext|>",
 
18
  "tokenizer_class": "GPT2Tokenizer",
 
 
19
  "unk_token": "<|endoftext|>"
20
  }
 
13
  "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
16
+ "max_length": 512,
17
  "model_max_length": 1024,
18
  "pad_token": "<|endoftext|>",
19
+ "stride": 0,
20
  "tokenizer_class": "GPT2Tokenizer",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
  "unk_token": "<|endoftext|>"
24
  }
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6352009773254395,
3
- "best_model_checkpoint": "./outputs/checkpoint-1000",
4
- "epoch": 0.7285974499089253,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -147,13 +147,27 @@
147
  "eval_samples_per_second": 43.549,
148
  "eval_steps_per_second": 5.449,
149
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 100,
153
  "max_steps": 4116,
154
  "num_train_epochs": 3,
155
  "save_steps": 100,
156
- "total_flos": 5.962359246697267e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }
 
1
  {
2
+ "best_metric": 1.6240431070327759,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1100",
4
+ "epoch": 0.8014571948998178,
5
  "eval_steps": 100,
6
+ "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
147
  "eval_samples_per_second": 43.549,
148
  "eval_steps_per_second": 5.449,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 1.6461,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 1.6240431070327759,
160
+ "eval_runtime": 293.5989,
161
+ "eval_samples_per_second": 21.369,
162
+ "eval_steps_per_second": 2.674,
163
+ "step": 1100
164
  }
165
  ],
166
  "logging_steps": 100,
167
  "max_steps": 4116,
168
  "num_train_epochs": 3,
169
  "save_steps": 100,
170
+ "total_flos": 6.557572892531098e+16,
171
  "trial_name": null,
172
  "trial_params": null
173
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:435ef416a520c327b44f1a335ae059bdb8b9a978d39dfecd5bff01684de2670c
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ab4a714067324690a64db56d021644d50462360424c147b3e9df6b69650fa0
3
  size 4155