SystemAdmin123 commited on
Commit
e4df262
·
verified ·
1 Parent(s): 4a5b1c3

Training in progress, step 120, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ed4a36b34b65821b08dff3948d1a639f0f562d4126a85ca547743b8a27190dd
3
  size 250490408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84bda531b872d67221b98bd6c658143e5d6cdef1cc3945a95e53e5b9f7dcd800
3
  size 250490408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb83c1ca5dbcaa0db6e445249be5922680eab3d9503f73ff1e43174909e16b5
3
  size 255265850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e9c5ada665a48d98e97c1e7fe956283af0da1e8c0bcc8349010ef07ff0fcc8
3
  size 255265850
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e4027fefb69e105f5311c9cb16f281c69cccb2a472492c81e3a929896e7e87d
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ab5f379178a16fe50394e3a25fed2ec2104fb031e0d65d050929ea3900b9b8a
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4791734ef084625a7f903446f63b41709ec4aa45432e4cf043c49101a53ddaee
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18d6d5030bddd3e14856faaed8b883ccb49a599678d6e4aaaec0ea4cbbea9e4
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b34b977f0b4e5c0c89d8dd446f627fbac9a5e7e945e487b3b1a5a2235e2ee07
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": 8.333333333333334,
5
  "eval_steps": 40,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -101,6 +101,28 @@
101
  "learning_rate": 0.00019264940672148018,
102
  "loss": 4.2197,
103
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
  }
105
  ],
106
  "logging_steps": 10,
@@ -120,7 +142,7 @@
120
  "attributes": {}
121
  }
122
  },
123
- "total_flos": 6486313364619264.0,
124
  "train_batch_size": 32,
125
  "trial_name": null,
126
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
  "eval_steps": 40,
6
+ "global_step": 120,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
101
  "learning_rate": 0.00019264940672148018,
102
  "loss": 4.2197,
103
  "step": 100
104
+ },
105
+ {
106
+ "epoch": 9.166666666666666,
107
+ "grad_norm": 4.625,
108
+ "learning_rate": 0.00019043571606975777,
109
+ "loss": 4.1157,
110
+ "step": 110
111
+ },
112
+ {
113
+ "epoch": 10.0,
114
+ "grad_norm": 4.40625,
115
+ "learning_rate": 0.0001879473751206489,
116
+ "loss": 4.015,
117
+ "step": 120
118
+ },
119
+ {
120
+ "epoch": 10.0,
121
+ "eval_loss": 3.147190570831299,
122
+ "eval_runtime": 10.4825,
123
+ "eval_samples_per_second": 143.191,
124
+ "eval_steps_per_second": 2.29,
125
+ "step": 120
126
  }
127
  ],
128
  "logging_steps": 10,
 
142
  "attributes": {}
143
  }
144
  },
145
+ "total_flos": 7772915311312896.0,
146
  "train_batch_size": 32,
147
  "trial_name": null,
148
  "trial_params": null