great0001 commited on
Commit
a6f7925
·
verified ·
1 Parent(s): 9f32931

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c877ce7b614ff069bfe4cf5a6d8f98a20eac92417e8f0a5167fb9588cdc29dba
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d106a92ecc370600a1220ace134eb375e981ee714f1406292270ba0bdcf081bc
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0736bf3c9f766420ea132c0415494594df7e35fad4363bd7eefb276ab47be91
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7561fb74700779db1d55ee07afb5439afdaa6a6674ca6cb3a6264c98f4ef7eee
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd197233abf432c0c23452d37e2c9eac62609b8e7d27929b13fe5bd30a4bf41
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2016bcdd9ab3768f545f9d12095da67be199dcc219634b31be42ed5524ee23f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 9.008603216071348e-05,
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,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 12.86,
45
  "eval_steps_per_second": 6.43,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1662257190666240.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00018017206432142696,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 12.86,
45
  "eval_steps_per_second": 6.43,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00012011470954761798,
50
+ "grad_norm": 0.27617770433425903,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.3775,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00015014338693452247,
57
+ "grad_norm": 0.33552882075309753,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.3013,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00018017206432142696,
64
+ "grad_norm": 0.31797710061073303,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.4089,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00018017206432142696,
71
+ "eval_loss": 0.3593178689479828,
72
+ "eval_runtime": 1091.0548,
73
+ "eval_samples_per_second": 12.852,
74
+ "eval_steps_per_second": 6.426,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3324514381332480.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null