rakhman-llm commited on
Commit
cf08598
·
verified ·
1 Parent(s): 16d5efc

Training in progress, step 9000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab1af3989a3cb0ef17441134c6d9115d239c28d341121ec54ddc157bc80ca31
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9ae7e86bbc77dbce22ca2c90f22880719186ccf1df5b938440f4fba479e8f8
3
  size 891558696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee7fd58185a25f322d89f31ab1205c29d56ebbe0608d01fbd4ed1810b096d21d
3
  size 1783272762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f073df4c55287ce71ca924a294e38b1ab7cc164a34073772713039d245568f
3
  size 1783272762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8142adb50de721c312198118970172331afa1dd03733dddae1b8e58019f13418
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343cbf433a49823c26aa4dd9334fa3e204370732996c7bb60db1a7158c5badde
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0999afe033f75d8bd9448190d8bb949c5c3397cd764ae214dd958ddb75be8cfe
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b8133c0078c9773a22c7a49b5547dc88d96e16d710eff8078381e482ecc029
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": 1.766417290108063,
5
  "eval_steps": 500,
6
- "global_step": 8500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -134,6 +134,13 @@
134
  "learning_rate": 8.229426433915213e-06,
135
  "loss": 0.355,
136
  "step": 8500
 
 
 
 
 
 
 
137
  }
138
  ],
139
  "logging_steps": 500,
@@ -153,7 +160,7 @@
153
  "attributes": {}
154
  }
155
  },
156
- "total_flos": 1.035167518162944e+16,
157
  "train_batch_size": 2,
158
  "trial_name": null,
159
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8703241895261846,
5
  "eval_steps": 500,
6
+ "global_step": 9000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
134
  "learning_rate": 8.229426433915213e-06,
135
  "loss": 0.355,
136
  "step": 8500
137
+ },
138
+ {
139
+ "epoch": 1.8703241895261846,
140
+ "grad_norm": 0.8178287148475647,
141
+ "learning_rate": 7.536713771127737e-06,
142
+ "loss": 0.3492,
143
+ "step": 9000
144
  }
145
  ],
146
  "logging_steps": 500,
 
160
  "attributes": {}
161
  }
162
  },
163
+ "total_flos": 1.096063307218944e+16,
164
  "train_batch_size": 2,
165
  "trial_name": null,
166
  "trial_params": null