ccore commited on
Commit
9804890
·
verified ·
1 Parent(s): 08c8747

Training in progress, epoch 8, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b25316505855cf494267aec09fdf57c4bff22da2b10f3795d92c589993260e93
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97927bf58117b9f4ec7080fdbd5bd3da2e4d8230ad0fb35f5e8709b889bb2988
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e5738f832083a74182d5df41d22d89c5a5617631cbcb54e511ee4c079370d48
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b0ec90550993f5bdeea2d600198f6e1e3e7da33644c6203a87be1e70067f33
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ed244f721b9495a7585428e681f68fc58fe0408c52158c97e3cc0c7c1263a36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e89c896d5de675a65aad5262ac3f12ebbd8dd5c6d70c67b825651cc5237f1b2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8ac4a1a7643d89921844755fac4df06257bb3227bbdd9eeb1bf3815ec0f7345
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf5c0688e2287321a723c9f3d9f4506c43f1a47090333ea07799426904724fe
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.30498865246772766,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-2254",
4
- "epoch": 7.0,
5
  "eval_steps": 500,
6
- "global_step": 2254,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -91,6 +91,21 @@
91
  "eval_samples_per_second": 19.744,
92
  "eval_steps_per_second": 4.936,
93
  "step": 2254
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  }
95
  ],
96
  "logging_steps": 500,
@@ -110,7 +125,7 @@
110
  "attributes": {}
111
  }
112
  },
113
- "total_flos": 9.399458267136e+16,
114
  "train_batch_size": 10,
115
  "trial_name": null,
116
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3037343919277191,
3
+ "best_model_checkpoint": "./opt_trained/checkpoint-2576",
4
+ "epoch": 8.0,
5
  "eval_steps": 500,
6
+ "global_step": 2576,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
91
  "eval_samples_per_second": 19.744,
92
  "eval_steps_per_second": 4.936,
93
  "step": 2254
94
+ },
95
+ {
96
+ "epoch": 7.765758754863813,
97
+ "grad_norm": 2.2369720935821533,
98
+ "learning_rate": 3.054517133956387e-05,
99
+ "loss": 0.3023,
100
+ "step": 2500
101
+ },
102
+ {
103
+ "epoch": 8.0,
104
+ "eval_loss": 0.3037343919277191,
105
+ "eval_runtime": 144.6161,
106
+ "eval_samples_per_second": 19.749,
107
+ "eval_steps_per_second": 4.937,
108
+ "step": 2576
109
  }
110
  ],
111
  "logging_steps": 500,
 
125
  "attributes": {}
126
  }
127
  },
128
+ "total_flos": 1.0742238019584e+17,
129
  "train_batch_size": 10,
130
  "trial_name": null,
131
  "trial_params": null