rakhman-llm commited on
Commit
4436634
1 Parent(s): 324665a

Training in progress, step 9500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05d0ea7a0f35f6452822d7ef39333323a4dfb3a99f01b82a901680f98583ce5e
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74dbc4fc66a0521c67117b743d8dee6d8791965619a98835f3f2c1874b66cb9c
3
  size 891558696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6381172a935f4d2ce146c253e91ff2c61e7331f3ee0f502a280fb40f35dedbb
3
  size 1783272762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b14e9e9ec67fc84b17a0cf8ac4351485843887f3332aa843d88f8792e88c06
3
  size 1783272762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:343cbf433a49823c26aa4dd9334fa3e204370732996c7bb60db1a7158c5badde
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b67c05f37b4606592392a2a2e3555caf2c285ee68c702566e4cb3524218561
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86b8133c0078c9773a22c7a49b5547dc88d96e16d710eff8078381e482ecc029
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ecb14aafa347554d588d4693c91cb65e2015d07059f19d3a2e8bd39a45c1a9
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": 1.8703241895261846,
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,
@@ -141,6 +141,13 @@
141
  "learning_rate": 7.536713771127737e-06,
142
  "loss": 0.3495,
143
  "step": 9000
 
 
 
 
 
 
 
144
  }
145
  ],
146
  "logging_steps": 500,
@@ -160,7 +167,7 @@
160
  "attributes": {}
161
  }
162
  },
163
- "total_flos": 1.096063307218944e+16,
164
  "train_batch_size": 2,
165
  "trial_name": null,
166
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.9742310889443058,
5
  "eval_steps": 500,
6
+ "global_step": 9500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
141
  "learning_rate": 7.536713771127737e-06,
142
  "loss": 0.3495,
143
  "step": 9000
144
+ },
145
+ {
146
+ "epoch": 1.9742310889443058,
147
+ "grad_norm": 1.4501579999923706,
148
+ "learning_rate": 6.845386533665836e-06,
149
+ "loss": 0.3385,
150
+ "step": 9500
151
  }
152
  ],
153
  "logging_steps": 500,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 1.156959096274944e+16,
171
  "train_batch_size": 2,
172
  "trial_name": null,
173
  "trial_params": null