modhp commited on
Commit
7b23241
Β·
1 Parent(s): 3c15f44

add tokenizer

Browse files
{checkpoint-1000 β†’ checkpoint-1500}/config.json RENAMED
File without changes
{checkpoint-1000 β†’ checkpoint-1500}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61d83187a1f813e570b8172202be132f9dc0f940a837641665703d14c5c904da
3
  size 721679569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254efd1bd850fbd13a92d4d704c28e38bf96a25312d2cea898bf0d5d3097fe07
3
  size 721679569
{checkpoint-1000 β†’ checkpoint-1500}/preprocessor_config.json RENAMED
File without changes
{checkpoint-1000 β†’ checkpoint-1500}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:973e9ac78b4070bbd43cb3872ccb15ad0f51d66f21e401675a74eb6c00746104
3
  size 377668631
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2e6339ab6117bda688c1a63f03c6e83139f47f7245e9ea64e50d11b2013a0b
3
  size 377668631
{checkpoint-1000 β†’ checkpoint-1500}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:918497def91b863e016b56685d7531de6045252ca14b1119353f10edbdd07d05
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f378c7f99d8466faf1aba279788bd3c802a0eb3176f3302961bd95cc94a08c47
3
  size 14567
{checkpoint-1000 β†’ checkpoint-1500}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb3c2d4cc9cd5db0ded821257afbbb9e216de72b23cbfad8f7530e40d4a66085
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5433c75dd2a5eb661891a22728e58238c70691115bede0539ebac1e487820e
3
  size 623
{checkpoint-1000 β†’ checkpoint-1500}/trainer_state.json RENAMED
@@ -1,46 +1,61 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.526315789473684,
5
- "global_step": 1000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 0.76,
12
  "learning_rate": 0.005,
13
- "loss": 12.1146,
14
  "step": 500
15
  },
16
  {
17
- "epoch": 0.76,
18
- "eval_loss": 6.7651519775390625,
19
- "eval_runtime": 549.3202,
20
- "eval_samples_per_second": 0.843,
21
- "eval_steps_per_second": 0.106,
22
  "eval_wer": 1.0,
23
  "step": 500
24
  },
25
  {
26
- "epoch": 1.53,
27
  "learning_rate": 0.01,
28
- "loss": 3.7548,
29
  "step": 1000
30
  },
31
  {
32
- "epoch": 1.53,
33
- "eval_loss": 4.368209362030029,
34
- "eval_runtime": 514.3478,
35
- "eval_samples_per_second": 0.9,
36
- "eval_steps_per_second": 0.113,
37
  "eval_wer": 1.0,
38
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
- "max_steps": 19650,
42
  "num_train_epochs": 30,
43
- "total_flos": 1.3443902730745056e+17,
44
  "trial_name": null,
45
  "trial_params": null
46
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.7162471395881007,
5
+ "global_step": 1500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.57,
12
  "learning_rate": 0.005,
13
+ "loss": 15.1526,
14
  "step": 500
15
  },
16
  {
17
+ "epoch": 0.57,
18
+ "eval_loss": 6.8601579666137695,
19
+ "eval_runtime": 621.735,
20
+ "eval_samples_per_second": 0.745,
21
+ "eval_steps_per_second": 0.093,
22
  "eval_wer": 1.0,
23
  "step": 500
24
  },
25
  {
26
+ "epoch": 1.14,
27
  "learning_rate": 0.01,
28
+ "loss": 4.0534,
29
  "step": 1000
30
  },
31
  {
32
+ "epoch": 1.14,
33
+ "eval_loss": 4.218315601348877,
34
+ "eval_runtime": 609.7294,
35
+ "eval_samples_per_second": 0.759,
36
+ "eval_steps_per_second": 0.095,
37
  "eval_wer": 1.0,
38
  "step": 1000
39
+ },
40
+ {
41
+ "epoch": 1.72,
42
+ "learning_rate": 0.009801744647105471,
43
+ "loss": 3.7639,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 1.72,
48
+ "eval_loss": 4.085240364074707,
49
+ "eval_runtime": 611.9711,
50
+ "eval_samples_per_second": 0.757,
51
+ "eval_steps_per_second": 0.095,
52
+ "eval_wer": 1.0,
53
+ "step": 1500
54
  }
55
  ],
56
+ "max_steps": 26220,
57
  "num_train_epochs": 30,
58
+ "total_flos": 1.5013768433244768e+17,
59
  "trial_name": null,
60
  "trial_params": null
61
  }
{checkpoint-1000 β†’ checkpoint-1500}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5090d2459c36fef37ff5438732de6290998bb02855c3984b89a4e1df893aa0c3
3
  size 2991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9690abd7f068da2d83484f52436af56487dd6638bfa2a2708c15a9ed63f367
3
  size 2991
runs/Apr08_17-52-44_TUF/1649465633.5198846/events.out.tfevents.1649465633.TUF.21348.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128e2744d16103304bc3b0f7a2c47574ebc703fc92ad80d2255e479b6a0d1d92
3
+ size 4782
runs/Apr08_17-52-44_TUF/events.out.tfevents.1649465633.TUF.21348.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628de3650cda02b8520dc61f6eb2fff3ab8e0e18cc9f219e21dc7f099eef1829
3
+ size 6438
vocab.json CHANGED
@@ -1 +1 @@
1
- {"z": 0, "l": 1, "t": 2, "e": 3, "c": 4, "w": 5, "i": 6, "g": 7, "d": 8, "r": 9, "j": 10, "y": 12, "p": 13, "m": 14, "h": 15, "k": 16, "f": 17, "a": 18, "'": 19, "q": 20, "x": 21, "o": 22, "u": 23, "v": 24, "n": 25, "s": 26, "b": 27, "[UNK]": 28, "[PAD]": 29, "|": 11}
 
1
+ {"y": 0, "j": 1, "z": 2, "'": 3, "b": 4, "g": 5, "v": 6, "r": 7, "a": 8, "p": 9, "e": 10, "q": 12, "c": 13, "m": 14, "u": 15, "f": 16, "i": 17, "k": 18, "d": 19, "x": 20, "w": 21, "t": 22, "n": 23, "s": 24, "l": 25, "h": 26, "o": 27, "[UNK]": 28, "[PAD]": 29, "|": 11}