oldiday commited on
Commit
5c94a99
·
verified ·
1 Parent(s): c66b2bb

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b4c33875e6fe9b2c99172b3029afbc7b22c07b4eb2862bc349614a1494dfb6d
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c6e0fa1fe23124e957d30d9dd4a4888ad417d78d5d5b86df0ad3407c1a3a34
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ee3b49445b00f060c8d00b1981dc4990e05cfee931d3a88309735e21cb933b7
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4063bb97ee3e64b28ed94b0c443d63755fca0f23da0be53e7351204ea8b682c8
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f4f0e8dad369bc7bb59d5e7f497c51f10df0b55006fce373720fb706b727122
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05de074c39f85666a0a560cfe9d1a3cb4d0dea668ee250ea7d270dcd0130b7ff
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
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": 0.08372093023255814,
5
  "eval_steps": 9,
6
- "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 36.414,
132
  "eval_steps_per_second": 4.577,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 9405135625125888.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10465116279069768,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 36.414,
132
  "eval_steps_per_second": 4.577,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.09069767441860466,
137
+ "grad_norm": 3.955404758453369,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 3.0893,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.09767441860465116,
144
+ "grad_norm": 3.391456365585327,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 2.924,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.10465116279069768,
151
+ "grad_norm": 3.183100461959839,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 2.8891,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.10465116279069768,
158
+ "eval_loss": 2.8821494579315186,
159
+ "eval_runtime": 19.8866,
160
+ "eval_samples_per_second": 36.406,
161
+ "eval_steps_per_second": 4.576,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 1.175641953140736e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null