kostiantynk1205 commited on
Commit
293bfa8
·
verified ·
1 Parent(s): 16e86ac

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 sha256:6c9347d4fb490e86d1b41847cab8d8a381bd5977758c3c902d64c5644acc7d58
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca676644eb6aaecbfcf45158090ff7a6edb74128f39e92fdca02f50ef6e1a6c
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:503f61cc57889818397a544cf039b33a5e21b1d1ebbe3783cb50c113d5ac4164
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959af66ba363d912352465d816060e757eedfa8fc8132aae43919b6d35592db9
3
  size 162868
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
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": 0.0011211809772960853,
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": 353.404,
45
  "eval_steps_per_second": 176.859,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 36168007680.0,
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": 0.0022423619545921705,
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": 353.404,
45
  "eval_steps_per_second": 176.859,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0014949079697281135,
50
+ "grad_norm": 2.0556488037109375,
51
+ "learning_rate": 8e-05,
52
+ "loss": 44.433,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.001868634962160142,
57
+ "grad_norm": 1.9328457117080688,
58
+ "learning_rate": 0.0001,
59
+ "loss": 44.4442,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0022423619545921705,
64
+ "grad_norm": 2.117732524871826,
65
+ "learning_rate": 0.00012,
66
+ "loss": 44.4806,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0022423619545921705,
71
+ "eval_loss": 11.112125396728516,
72
+ "eval_runtime": 3.2626,
73
+ "eval_samples_per_second": 345.427,
74
+ "eval_steps_per_second": 172.867,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 69924814848.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null