timewanderer commited on
Commit
3f8552d
1 Parent(s): d7e71e9

Training in progress, step 1000

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33620587b37c196969d3f412f74ef041dcfeee8258db5933dc3c4540e70b1e43
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2265efdbd127f32817bf80110d8d6f541a55048b2e22b7e0e6227a688a9ef047
3
  size 268290900
run-0/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:847b25893f634ae7ae19c7fa981b031b671da55fceaff107c9c6fd1535ba9bd9
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2265efdbd127f32817bf80110d8d6f541a55048b2e22b7e0e6227a688a9ef047
3
  size 268290900
run-0/checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbdf97ee43485482022c7936b134134b1d804f6bddceb5646e66726f0d638653
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4557295dc599e62a6393fbd116ab5c4958396bbe86258e055f7094ff579a4f6
3
  size 536643898
run-0/checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f182501c34e4ea3ebc7617d27edab7e1367582b147e518cd90295ec7f2eaa0f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a4307cca951ef6d42c7f184774e8b1259c78b2bf130b8443ec0b62f6dbf689
3
  size 1064
run-0/checkpoint-1000/trainer_state.json CHANGED
@@ -10,50 +10,50 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6083870967741936,
14
- "eval_loss": 0.26111724972724915,
15
- "eval_runtime": 5.07,
16
- "eval_samples_per_second": 611.445,
17
- "eval_steps_per_second": 12.821,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.612690269947052,
23
- "learning_rate": 1.371069182389937e-05,
24
- "loss": 0.4067,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8261290322580646,
30
- "eval_loss": 0.1251312643289566,
31
- "eval_runtime": 5.2675,
32
- "eval_samples_per_second": 588.512,
33
- "eval_steps_per_second": 12.34,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8719354838709678,
39
- "eval_loss": 0.08443494886159897,
40
- "eval_runtime": 5.1546,
41
- "eval_samples_per_second": 601.399,
42
- "eval_steps_per_second": 12.61,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.5761224031448364,
48
- "learning_rate": 7.421383647798742e-06,
49
- "loss": 0.1453,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
- "max_steps": 1590,
55
  "num_input_tokens_seen": 0,
56
- "num_train_epochs": 5,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
@@ -67,12 +67,12 @@
67
  "attributes": {}
68
  }
69
  },
70
- "total_flos": 260941334653608.0,
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
- "alpha": 0.006505868879858823,
75
- "num_train_epochs": 5,
76
- "temperature": 4
77
  }
78
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5887096774193549,
14
+ "eval_loss": 0.19886387884616852,
15
+ "eval_runtime": 5.1732,
16
+ "eval_samples_per_second": 599.241,
17
+ "eval_steps_per_second": 12.565,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5294517874717712,
23
+ "learning_rate": 1.650593990216632e-05,
24
+ "loss": 0.3203,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8193548387096774,
30
+ "eval_loss": 0.09618715196847916,
31
+ "eval_runtime": 5.2244,
32
+ "eval_samples_per_second": 593.365,
33
+ "eval_steps_per_second": 12.442,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8783870967741936,
39
+ "eval_loss": 0.06421981006860733,
40
+ "eval_runtime": 5.1205,
41
+ "eval_samples_per_second": 605.405,
42
+ "eval_steps_per_second": 12.694,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.44660821557044983,
48
+ "learning_rate": 1.3011879804332637e-05,
49
+ "loss": 0.1116,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
+ "max_steps": 2862,
55
  "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 9,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
 
67
  "attributes": {}
68
  }
69
  },
70
+ "total_flos": 370580110546716.0,
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
+ "alpha": 0.260556849082234,
75
+ "num_train_epochs": 9,
76
+ "temperature": 11
77
  }
78
  }
run-0/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffe43401e68c8a3628adf33b38f6ac638a3a3f3bc1dcbe05d52f58aece31629f
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a815016dfca6056394449b7eec53142e869a6e9ff738e6f9557bb4382010c025
3
  size 5240
runs/Oct11_17-03-17_c179252869f4/events.out.tfevents.1728666603.c179252869f4.732.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7029f09599f213efddf9c26859a245fd81796dbbf556a04ffae4cf4a5d4ca09b
3
- size 25652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4607fd143d4548a3c3e4f485b963b6458f636733bf845fc8a3470c8ce7d81a
3
+ size 26509