Commit
•
84d141c
1
Parent(s):
7f80a89
Training in progress, step 3600, 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 +21 -3
- last-checkpoint/tokenizer.json +6 -1
- last-checkpoint/trainer_state.json +10 -80
- 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab272531ca4f7f21d89ada6774e8e5bc07ab11ecffda04d158c5f53998ca655d
|
3 |
size 50338848
|
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:c562f3b307809fe2836dff271710f225ad458098595e0784fc6a7f5379d7ae0b
|
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:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0fe9debfc0931dca2aebaaa146c3890943a5809c00b1b2ba715c1a4eb6e57da
|
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 sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
|
3 |
size 627
|
last-checkpoint/special_tokens_map.json
CHANGED
@@ -1,6 +1,24 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
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.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
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,
|
@@ -501,93 +501,23 @@
|
|
501 |
{
|
502 |
"epoch": 2.62,
|
503 |
"learning_rate": 0.0002,
|
504 |
-
"loss": 1.
|
505 |
"step": 3600
|
506 |
},
|
507 |
{
|
508 |
"epoch": 2.62,
|
509 |
-
"eval_loss": 1.
|
510 |
-
"eval_runtime":
|
511 |
-
"eval_samples_per_second":
|
512 |
-
"eval_steps_per_second": 5.
|
513 |
"step": 3600
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"epoch": 2.7,
|
517 |
-
"learning_rate": 0.0002,
|
518 |
-
"loss": 1.225,
|
519 |
-
"step": 3700
|
520 |
-
},
|
521 |
-
{
|
522 |
-
"epoch": 2.7,
|
523 |
-
"eval_loss": 1.2477346658706665,
|
524 |
-
"eval_runtime": 143.7426,
|
525 |
-
"eval_samples_per_second": 43.647,
|
526 |
-
"eval_steps_per_second": 5.461,
|
527 |
-
"step": 3700
|
528 |
-
},
|
529 |
-
{
|
530 |
-
"epoch": 2.77,
|
531 |
-
"learning_rate": 0.0002,
|
532 |
-
"loss": 1.2032,
|
533 |
-
"step": 3800
|
534 |
-
},
|
535 |
-
{
|
536 |
-
"epoch": 2.77,
|
537 |
-
"eval_loss": 1.2393803596496582,
|
538 |
-
"eval_runtime": 148.064,
|
539 |
-
"eval_samples_per_second": 42.374,
|
540 |
-
"eval_steps_per_second": 5.302,
|
541 |
-
"step": 3800
|
542 |
-
},
|
543 |
-
{
|
544 |
-
"epoch": 2.84,
|
545 |
-
"learning_rate": 0.0002,
|
546 |
-
"loss": 1.2152,
|
547 |
-
"step": 3900
|
548 |
-
},
|
549 |
-
{
|
550 |
-
"epoch": 2.84,
|
551 |
-
"eval_loss": 1.2263625860214233,
|
552 |
-
"eval_runtime": 143.4886,
|
553 |
-
"eval_samples_per_second": 43.725,
|
554 |
-
"eval_steps_per_second": 5.471,
|
555 |
-
"step": 3900
|
556 |
-
},
|
557 |
-
{
|
558 |
-
"epoch": 2.91,
|
559 |
-
"learning_rate": 0.0002,
|
560 |
-
"loss": 1.1959,
|
561 |
-
"step": 4000
|
562 |
-
},
|
563 |
-
{
|
564 |
-
"epoch": 2.91,
|
565 |
-
"eval_loss": 1.2177170515060425,
|
566 |
-
"eval_runtime": 143.5576,
|
567 |
-
"eval_samples_per_second": 43.704,
|
568 |
-
"eval_steps_per_second": 5.468,
|
569 |
-
"step": 4000
|
570 |
-
},
|
571 |
-
{
|
572 |
-
"epoch": 2.99,
|
573 |
-
"learning_rate": 0.0002,
|
574 |
-
"loss": 1.1936,
|
575 |
-
"step": 4100
|
576 |
-
},
|
577 |
-
{
|
578 |
-
"epoch": 2.99,
|
579 |
-
"eval_loss": 1.205187439918518,
|
580 |
-
"eval_runtime": 143.4816,
|
581 |
-
"eval_samples_per_second": 43.727,
|
582 |
-
"eval_steps_per_second": 5.471,
|
583 |
-
"step": 4100
|
584 |
}
|
585 |
],
|
586 |
"logging_steps": 100,
|
587 |
"max_steps": 4116,
|
588 |
"num_train_epochs": 3,
|
589 |
"save_steps": 100,
|
590 |
-
"total_flos": 2.
|
591 |
"trial_name": null,
|
592 |
"trial_params": null
|
593 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2722229957580566,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3500",
|
4 |
+
"epoch": 2.62367941712204,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
501 |
{
|
502 |
"epoch": 2.62,
|
503 |
"learning_rate": 0.0002,
|
504 |
+
"loss": 1.3031,
|
505 |
"step": 3600
|
506 |
},
|
507 |
{
|
508 |
"epoch": 2.62,
|
509 |
+
"eval_loss": 1.3205279111862183,
|
510 |
+
"eval_runtime": 138.0704,
|
511 |
+
"eval_samples_per_second": 45.441,
|
512 |
+
"eval_steps_per_second": 5.686,
|
513 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
514 |
}
|
515 |
],
|
516 |
"logging_steps": 100,
|
517 |
"max_steps": 4116,
|
518 |
"num_train_epochs": 3,
|
519 |
"save_steps": 100,
|
520 |
+
"total_flos": 2.146160479353815e+17,
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
523 |
}
|
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 sha256:8359692bdb4a6bb3efa0d10dd8036b5f919a9ea002e4dc4eb94a27d30c9b489f
|
3 |
size 4219
|