Hugging Face's logo

nttx
/
4e65dfe5-e77f-42e6-9a9f-bd0dba0b0237

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
nttx commited on
Commit
d41e1b6
·
verified ·
1 Parent(s): a6f395a

Training in progress, step 2700, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +20 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cee22b4b79a96b59a7c881197c6d12ff951dbbc451ef288d700a15990a6a8502
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7350d1b2818baa194908d604eef7d306d0bfda5a977b25f0ba8f3ee19c68e643
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e23164c62b68b83dff7caf350e31d539e1bdcef5e17d29334364b12f14a13b8f
3
  size 39462
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efe7f84caa469288758d729267e555e7d4959d5bd9b77991c6b054571b2b94e
3
  size 39462
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8596957d61019869f86624316944f7cc105ea7be6406804df1d539d7bfe10133
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1bfd7bc146b83962f8ea49d8335d7e42b9e02cb8c55d49480bb5d6fb1f3eb70
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5de6bf0856eef74c5cae3e10b1dc9ce71fd688f258e1a1705f8e7bbc20c7025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c411a66287d4fb76303ae5ba8fbc6149ecf0ea6d0ba0f17e45b450c5260043f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.91218090057373,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-2400",
4
- "epoch": 4.010853683990816,
5
  "eval_steps": 300,
6
- "global_step": 2400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -135,6 +135,21 @@
135
  "eval_samples_per_second": 209.202,
136
  "eval_steps_per_second": 26.228,
137
  "step": 2400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
138
  }
139
  ],
140
  "logging_steps": 300,
@@ -163,7 +178,7 @@
163
  "attributes": {}
164
  }
165
  },
166
- "total_flos": 4537398067200.0,
167
  "train_batch_size": 8,
168
  "trial_name": null,
169
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.912158012390137,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-2700",
4
+ "epoch": 4.511792945105406,
5
  "eval_steps": 300,
6
+ "global_step": 2700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
135
  "eval_samples_per_second": 209.202,
136
  "eval_steps_per_second": 26.228,
137
  "step": 2400
138
+ },
139
+ {
140
+ "epoch": 4.511792945105406,
141
+ "grad_norm": 0.012792945839464664,
142
+ "learning_rate": 1.0469365763439531e-05,
143
+ "loss": 11.9128,
144
+ "step": 2700
145
+ },
146
+ {
147
+ "epoch": 4.511792945105406,
148
+ "eval_loss": 11.912158012390137,
149
+ "eval_runtime": 9.6282,
150
+ "eval_samples_per_second": 209.592,
151
+ "eval_steps_per_second": 26.277,
152
+ "step": 2700
153
  }
154
  ],
155
  "logging_steps": 300,
 
178
  "attributes": {}
179
  }
180
  },
181
+ "total_flos": 5104572825600.0,
182
  "train_batch_size": 8,
183
  "trial_name": null,
184
  "trial_params": null