Best000 commited on
Commit
5fca356
·
verified ·
1 Parent(s): 1be655b

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:a79d8379bb91d20b9e573354dbe7287d344df8d5cf8592468a9254edb3198efd
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9dde226828a229791c1e5a6a4ee1b8f07ecb0daf54bb7cf4359c0eaec570f0
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:643f2480ea37b71e499cc2404afbc0ec8e92f2dddd057ca42f1f1efaa6156236
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035ce60075b40211ed9198eb6e1fed739d2b11b6d3c24e49a615b5f76635d3d9
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2771d41fabe3267dcc30e3934f8016bf7a5aecc59b574bad9700580dd4f9b25
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27720904725670a8b0a696773696a672d9d3226e767b4c77713d801442ed152
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": 0.0006279106273873685,
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": 26.872,
45
  "eval_steps_per_second": 13.436,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 262551098621952.0,
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": 0.001255821254774737,
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": 26.872,
45
  "eval_steps_per_second": 13.436,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0008372141698498247,
50
+ "grad_norm": 1.8883458375930786,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.6434,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0010465177123122808,
57
+ "grad_norm": 1.859239935874939,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.6609,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.001255821254774737,
64
+ "grad_norm": 1.732227087020874,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.4172,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.001255821254774737,
71
+ "eval_loss": 2.3991305828094482,
72
+ "eval_runtime": 74.9832,
73
+ "eval_samples_per_second": 26.833,
74
+ "eval_steps_per_second": 13.416,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 550107063779328.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null