lesso commited on
Commit
6f77036
1 Parent(s): a7b5078

Training in progress, step 2, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "k_proj",
24
- "down_proj",
25
  "up_proj",
26
- "v_proj",
27
- "q_proj",
28
- "o_proj",
29
- "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
24
+ "q_proj",
25
  "k_proj",
26
+ "gate_proj",
27
  "up_proj",
28
+ "down_proj",
29
+ "v_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 sha256:76471e347673753046a228d4d25806deaeaca443962ce9a5b5e99df33e3a2e84
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd11b513214d933db443ffb11fab092e4d6a61996f946075a0ace8f578a6b93
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7bd37490f89591e3a3c2987e123edb6afbe74987c8ba694fa4d554ae38e655a
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3220425797c34586c09a9c059365760d75bf52f11239d1f2ef0be6ef893e064
3
  size 168037178
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ac0c668385ad2b9aa96b4a6520400841eeb43e87268e46a61e0b348e499755
3
+ size 14512
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ecbb76344ff458defacd3ba4d074ae53be644437725a0992f0f61f74c5530f
3
+ size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,56 +1,49 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.25,
5
- "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.08333333333333333,
13
  "grad_norm": NaN,
14
  "learning_rate": 0.0,
15
- "loss": 1.4924,
16
  "step": 1
17
  },
18
  {
19
- "epoch": 0.08333333333333333,
20
- "eval_loss": 1.4975985288619995,
21
- "eval_runtime": 0.1911,
22
- "eval_samples_per_second": 15.701,
23
- "eval_steps_per_second": 15.701,
24
  "step": 1
25
  },
26
  {
27
- "epoch": 0.16666666666666666,
28
- "grad_norm": 5.183752536773682,
29
  "learning_rate": 2e-05,
30
- "loss": 1.3074,
31
  "step": 2
32
  },
33
  {
34
- "epoch": 0.25,
35
- "grad_norm": 6.239664077758789,
36
- "learning_rate": 4e-05,
37
- "loss": 1.5739,
38
- "step": 3
39
- },
40
- {
41
- "epoch": 0.25,
42
- "eval_loss": 1.4466005563735962,
43
- "eval_runtime": 0.211,
44
- "eval_samples_per_second": 14.216,
45
- "eval_steps_per_second": 14.216,
46
- "step": 3
47
  }
48
  ],
49
  "logging_steps": 1,
50
- "max_steps": 10,
51
  "num_input_tokens_seen": 0,
52
  "num_train_epochs": 1,
53
- "save_steps": 3,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
56
  "args": {
@@ -63,7 +56,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 554869274443776.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3333333333333333,
5
+ "eval_steps": 2,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.16666666666666666,
13
  "grad_norm": NaN,
14
  "learning_rate": 0.0,
15
+ "loss": 1.3997,
16
  "step": 1
17
  },
18
  {
19
+ "epoch": 0.16666666666666666,
20
+ "eval_loss": 1.4973297119140625,
21
+ "eval_runtime": 0.2886,
22
+ "eval_samples_per_second": 10.395,
23
+ "eval_steps_per_second": 6.93,
24
  "step": 1
25
  },
26
  {
27
+ "epoch": 0.3333333333333333,
28
+ "grad_norm": 5.478867530822754,
29
  "learning_rate": 2e-05,
30
+ "loss": 1.4535,
31
  "step": 2
32
  },
33
  {
34
+ "epoch": 0.3333333333333333,
35
+ "eval_loss": 1.4973297119140625,
36
+ "eval_runtime": 0.284,
37
+ "eval_samples_per_second": 10.565,
38
+ "eval_steps_per_second": 7.043,
39
+ "step": 2
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
43
+ "max_steps": 6,
44
  "num_input_tokens_seen": 0,
45
  "num_train_epochs": 1,
46
+ "save_steps": 2,
47
  "stateful_callbacks": {
48
  "TrainerControl": {
49
  "args": {
 
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 739825699258368.0,
60
  "train_batch_size": 1,
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:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74dcf4a29346d06a18985986c93532599870827345febcfc1739afefe0e2e2b9
3
  size 6776