Hugging Face's logo

duyphu
/
dd99cfae-4152-4304-b09a-31a00951788f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
474ce88
·
verified ·
1 Parent(s): 306d192

Training in progress, step 13, checkpoint

Browse files
Files changed (7) hide show
  1. last-checkpoint/adapter_config.json +4 -4
  2. last-checkpoint/adapter_model.safetensors +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/rng_state.pth +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +32 -10
  7. last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
 
24
  "up_proj",
 
25
  "o_proj",
26
  "down_proj",
27
- "gate_proj",
28
- "q_proj",
29
- "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
+ "gate_proj",
25
  "up_proj",
26
+ "q_proj",
27
  "o_proj",
28
  "down_proj",
29
+ "k_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c33d763c0617a394d15b9346deed8a03e779671ae876d825a4934ac6de97a986
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b317a4ed15ab8a58797a5e0e6de3a33d7a0482c55d796cc768bd74896c1abb01
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b602ed550f0622d93be0da741793ea2a0876b8f8e9db647323a2ba54310c9fed
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afee6da0e5ac98b83474d2a2ae9258a58f891a405483d9baf3fe6afef2c3a50
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baecc8988a2f594185c875288190c60274795754df975adfaa0c8b19740a1a71
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0014342058085335247,
5
- "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,17 +11,39 @@
11
  {
12
  "epoch": 0.0014342058085335247,
13
  "eval_loss": 6.945818901062012,
14
- "eval_runtime": 37.5898,
15
- "eval_samples_per_second": 7.821,
16
- "eval_steps_per_second": 3.911,
17
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 5,
21
- "max_steps": 1,
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
- "save_steps": 1,
25
  "stateful_callbacks": {
26
  "TrainerControl": {
27
  "args": {
@@ -29,12 +51,12 @@
29
  "should_evaluate": false,
30
  "should_log": false,
31
  "should_save": true,
32
- "should_training_stop": true
33
  },
34
  "attributes": {}
35
  }
36
  },
37
- "total_flos": 369912849629184.0,
38
  "train_batch_size": 2,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01864467551093582,
5
+ "eval_steps": 10,
6
+ "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.0014342058085335247,
13
  "eval_loss": 6.945818901062012,
14
+ "eval_runtime": 37.617,
15
+ "eval_samples_per_second": 7.816,
16
+ "eval_steps_per_second": 3.908,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.007171029042667623,
21
+ "grad_norm": 1.6862187385559082,
22
+ "learning_rate": 5e-05,
23
+ "loss": 2.2368,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.014342058085335245,
28
+ "grad_norm": 3.357865810394287,
29
+ "learning_rate": 0.0001,
30
+ "loss": 2.148,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.014342058085335245,
35
+ "eval_loss": 5.640789985656738,
36
+ "eval_runtime": 38.0049,
37
+ "eval_samples_per_second": 7.736,
38
+ "eval_steps_per_second": 3.868,
39
+ "step": 10
40
  }
41
  ],
42
  "logging_steps": 5,
43
+ "max_steps": 50,
44
  "num_input_tokens_seen": 0,
45
  "num_train_epochs": 1,
46
+ "save_steps": 13,
47
  "stateful_callbacks": {
48
  "TrainerControl": {
49
  "args": {
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": false
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 4762627938975744.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e00de3df2ed8df0945a7be59f4fcc3fbf8969fd91fab478768805f80f8491fc
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf77c1733da49b768604912e40c24244060bcba791ea62849b69c70ca50a78a6
3
  size 6776