Commit
•
e992e89
1
Parent(s):
7bb504a
Training in progress, step 3100, checkpoint
Browse files- last-checkpoint/README.md +0 -12
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/special_tokens_map.json +7 -1
- last-checkpoint/tokenizer_config.json +5 -1
- last-checkpoint/trainer_state.json +10 -66
- last-checkpoint/training_args.bin +1 -1
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.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 75507072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:153147260199c704e8bfd106addf0bce7dd09e996a0b77778bff08d6d95bc8c8
|
3 |
size 75507072
|
last-checkpoint/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 sha256:2f8382c25b1ec233f3d8dde2bd7aaeff523df68b0959f1aa2b74feb2306b777e
|
3 |
+
size 151032837
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab6b545b6dd6418e570a8474ea31c45a1baed67ab97da8014ad68491fbcf9bed
|
3 |
size 14575
|
last-checkpoint/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 sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
|
3 |
size 627
|
last-checkpoint/special_tokens_map.json
CHANGED
@@ -12,6 +12,12 @@
|
|
12 |
">>SUFFIX<<",
|
13 |
">>MIDDLE<<"
|
14 |
],
|
15 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"pad_token": "<|endoftext|>"
|
17 |
}
|
|
|
12 |
">>SUFFIX<<",
|
13 |
">>MIDDLE<<"
|
14 |
],
|
15 |
+
"eos_token": {
|
16 |
+
"content": "<|endoftext|>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
"pad_token": "<|endoftext|>"
|
23 |
}
|
last-checkpoint/tokenizer_config.json
CHANGED
@@ -113,11 +113,15 @@
|
|
113 |
],
|
114 |
"clean_up_tokenization_spaces": true,
|
115 |
"eos_token": "<|endoftext|>",
|
|
|
116 |
"model_input_names": [
|
117 |
"input_ids",
|
118 |
"attention_mask"
|
119 |
],
|
120 |
"model_max_length": 2048,
|
121 |
"pad_token": "<|endoftext|>",
|
122 |
-
"
|
|
|
|
|
|
|
123 |
}
|
|
|
113 |
],
|
114 |
"clean_up_tokenization_spaces": true,
|
115 |
"eos_token": "<|endoftext|>",
|
116 |
+
"max_length": 512,
|
117 |
"model_input_names": [
|
118 |
"input_ids",
|
119 |
"attention_mask"
|
120 |
],
|
121 |
"model_max_length": 2048,
|
122 |
"pad_token": "<|endoftext|>",
|
123 |
+
"stride": 0,
|
124 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
125 |
+
"truncation_side": "right",
|
126 |
+
"truncation_strategy": "longest_first"
|
127 |
}
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -431,79 +431,23 @@
|
|
431 |
{
|
432 |
"epoch": 2.26,
|
433 |
"learning_rate": 0.0002,
|
434 |
-
"loss": 1.
|
435 |
"step": 3100
|
436 |
},
|
437 |
{
|
438 |
"epoch": 2.26,
|
439 |
-
"eval_loss": 1.
|
440 |
-
"eval_runtime":
|
441 |
-
"eval_samples_per_second":
|
442 |
-
"eval_steps_per_second":
|
443 |
"step": 3100
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 2.33,
|
447 |
-
"learning_rate": 0.0002,
|
448 |
-
"loss": 1.1423,
|
449 |
-
"step": 3200
|
450 |
-
},
|
451 |
-
{
|
452 |
-
"epoch": 2.33,
|
453 |
-
"eval_loss": 1.1581230163574219,
|
454 |
-
"eval_runtime": 425.212,
|
455 |
-
"eval_samples_per_second": 14.755,
|
456 |
-
"eval_steps_per_second": 1.846,
|
457 |
-
"step": 3200
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 2.4,
|
461 |
-
"learning_rate": 0.0002,
|
462 |
-
"loss": 1.1262,
|
463 |
-
"step": 3300
|
464 |
-
},
|
465 |
-
{
|
466 |
-
"epoch": 2.4,
|
467 |
-
"eval_loss": 1.147517442703247,
|
468 |
-
"eval_runtime": 424.8484,
|
469 |
-
"eval_samples_per_second": 14.768,
|
470 |
-
"eval_steps_per_second": 1.848,
|
471 |
-
"step": 3300
|
472 |
-
},
|
473 |
-
{
|
474 |
-
"epoch": 2.48,
|
475 |
-
"learning_rate": 0.0002,
|
476 |
-
"loss": 1.1114,
|
477 |
-
"step": 3400
|
478 |
-
},
|
479 |
-
{
|
480 |
-
"epoch": 2.48,
|
481 |
-
"eval_loss": 1.1388046741485596,
|
482 |
-
"eval_runtime": 418.7042,
|
483 |
-
"eval_samples_per_second": 14.984,
|
484 |
-
"eval_steps_per_second": 1.875,
|
485 |
-
"step": 3400
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 2.55,
|
489 |
-
"learning_rate": 0.0002,
|
490 |
-
"loss": 1.1112,
|
491 |
-
"step": 3500
|
492 |
-
},
|
493 |
-
{
|
494 |
-
"epoch": 2.55,
|
495 |
-
"eval_loss": 1.128933310508728,
|
496 |
-
"eval_runtime": 418.5353,
|
497 |
-
"eval_samples_per_second": 14.99,
|
498 |
-
"eval_steps_per_second": 1.876,
|
499 |
-
"step": 3500
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 100,
|
503 |
"max_steps": 4116,
|
504 |
"num_train_epochs": 3,
|
505 |
"save_steps": 100,
|
506 |
-
"total_flos": 1.
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.175557017326355,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3000",
|
4 |
+
"epoch": 2.2593806921675776,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
431 |
{
|
432 |
"epoch": 2.26,
|
433 |
"learning_rate": 0.0002,
|
434 |
+
"loss": 1.1799,
|
435 |
"step": 3100
|
436 |
},
|
437 |
{
|
438 |
"epoch": 2.26,
|
439 |
+
"eval_loss": 1.1915525197982788,
|
440 |
+
"eval_runtime": 341.6989,
|
441 |
+
"eval_samples_per_second": 18.361,
|
442 |
+
"eval_steps_per_second": 2.297,
|
443 |
"step": 3100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
444 |
}
|
445 |
],
|
446 |
"logging_steps": 100,
|
447 |
"max_steps": 4116,
|
448 |
"num_train_epochs": 3,
|
449 |
"save_steps": 100,
|
450 |
+
"total_flos": 1.0050808386648453e+18,
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac18d79547677891adc0e1a81cd6b672e7bb00fb497880f12dac0fd79be710c2
|
3 |
size 4219
|