Hugging Face's logo

alignment-handbook
/
zephyr-7b-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
Metrics Community
2
lewtun HF Staff commited on
Commit
0376e79
·
1 Parent(s): dc7d417

Model save

Browse files
Files changed (10) hide show
  1. all_results.json +8 -8
  2. eval_results.json +4 -4
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. runs/Jan09_00-05-47_ip-26-0-164-18/events.out.tfevents.1704758820.ip-26-0-164-18.2771624.0 +3 -0
  7. runs/Jan09_00-05-47_ip-26-0-164-18/events.out.tfevents.1704759527.ip-26-0-164-18.2771624.1 +3 -0
  8. train_results.json +4 -4
  9. trainer_state.json +10 -10
  10. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.9352964162826538,
4
- "eval_runtime": 142.6698,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 108.159,
7
- "eval_steps_per_second": 1.696,
8
- "train_loss": 0.9776264188486502,
9
- "train_runtime": 5607.0774,
10
  "train_samples": 207865,
11
- "train_samples_per_second": 24.866,
12
- "train_steps_per_second": 0.194
13
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.9352946281433105,
4
+ "eval_runtime": 142.3405,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 108.409,
7
+ "eval_steps_per_second": 1.7,
8
+ "train_loss": 0.07620820999145508,
9
+ "train_runtime": 563.6077,
10
  "train_samples": 207865,
11
+ "train_samples_per_second": 247.381,
12
+ "train_steps_per_second": 1.934
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.9352964162826538,
4
- "eval_runtime": 142.6698,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 108.159,
7
- "eval_steps_per_second": 1.696
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.9352946281433105,
4
+ "eval_runtime": 142.3405,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 108.409,
7
+ "eval_steps_per_second": 1.7
8
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:232137bac03db8babd334c175eaf9c7d7e387d1dd6f2abfbe48e207f4a443b31
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad03c68e305895320be8556507a5c7fe172be4c848b327e7154482a0e051600
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4fe60091d09e1119bf778cc2369ad70d1980397bb09eecf1c58426cf6ac5903
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3442a9f89309cb48f3c120d06169c98cf42e0f0bb185ad262da6eaf5b65e217d
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9636ee8013b50a24f25927cb38b16d2dc39cca8c2dad8c768b6ad96ed99cb8e
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5a61a77bbe6ccdcc60aacbb76e657e45c1a17ea23a8fd93bf7fe3ff861d5ad
3
  size 4540516344
runs/Jan09_00-05-47_ip-26-0-164-18/events.out.tfevents.1704758820.ip-26-0-164-18.2771624.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a8c062eeddc8854efc1993700a0cd5e0c9e4418568d1982171c3ca73dc2408
3
+ size 7900
runs/Jan09_00-05-47_ip-26-0-164-18/events.out.tfevents.1704759527.ip-26-0-164-18.2771624.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf2610b4cfe40702a5bc0ffb88392d4d1bb991b8424589c61f2babe872475c9
3
+ size 359
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.9776264188486502,
4
- "train_runtime": 5607.0774,
5
  "train_samples": 207865,
6
- "train_samples_per_second": 24.866,
7
- "train_steps_per_second": 0.194
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.07620820999145508,
4
+ "train_runtime": 563.6077,
5
  "train_samples": 207865,
6
+ "train_samples_per_second": 247.381,
7
+ "train_steps_per_second": 1.934
8
  }
trainer_state.json CHANGED
@@ -1253,7 +1253,7 @@
1253
  {
1254
  "epoch": 0.95,
1255
  "learning_rate": 1.5471558192656776e-07,
1256
- "loss": 0.9228,
1257
  "step": 1035
1258
  },
1259
  {
@@ -1283,7 +1283,7 @@
1283
  {
1284
  "epoch": 0.97,
1285
  "learning_rate": 4.6114783273213395e-08,
1286
- "loss": 0.9213,
1287
  "step": 1060
1288
  },
1289
  {
@@ -1301,7 +1301,7 @@
1301
  {
1302
  "epoch": 0.99,
1303
  "learning_rate": 1.1535349032167908e-08,
1304
- "loss": 0.9243,
1305
  "step": 1075
1306
  },
1307
  {
@@ -1324,9 +1324,9 @@
1324
  },
1325
  {
1326
  "epoch": 1.0,
1327
- "eval_loss": 0.9352964162826538,
1328
- "eval_runtime": 143.3874,
1329
- "eval_samples_per_second": 107.618,
1330
  "eval_steps_per_second": 1.688,
1331
  "step": 1090
1332
  },
@@ -1334,10 +1334,10 @@
1334
  "epoch": 1.0,
1335
  "step": 1090,
1336
  "total_flos": 456447649382400.0,
1337
- "train_loss": 0.9776264188486502,
1338
- "train_runtime": 5607.0774,
1339
- "train_samples_per_second": 24.866,
1340
- "train_steps_per_second": 0.194
1341
  }
1342
  ],
1343
  "logging_steps": 5,
 
1253
  {
1254
  "epoch": 0.95,
1255
  "learning_rate": 1.5471558192656776e-07,
1256
+ "loss": 0.9229,
1257
  "step": 1035
1258
  },
1259
  {
 
1283
  {
1284
  "epoch": 0.97,
1285
  "learning_rate": 4.6114783273213395e-08,
1286
+ "loss": 0.9212,
1287
  "step": 1060
1288
  },
1289
  {
 
1301
  {
1302
  "epoch": 0.99,
1303
  "learning_rate": 1.1535349032167908e-08,
1304
+ "loss": 0.9244,
1305
  "step": 1075
1306
  },
1307
  {
 
1324
  },
1325
  {
1326
  "epoch": 1.0,
1327
+ "eval_loss": 0.9352946281433105,
1328
+ "eval_runtime": 143.3511,
1329
+ "eval_samples_per_second": 107.645,
1330
  "eval_steps_per_second": 1.688,
1331
  "step": 1090
1332
  },
 
1334
  "epoch": 1.0,
1335
  "step": 1090,
1336
  "total_flos": 456447649382400.0,
1337
+ "train_loss": 0.07620820999145508,
1338
+ "train_runtime": 563.6077,
1339
+ "train_samples_per_second": 247.381,
1340
+ "train_steps_per_second": 1.934
1341
  }
1342
  ],
1343
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bee1621f45139ee240b3b0c153fd74fc82c8acd6484b3289c3f2aae89773e166
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dce10ff4431e31a8ad450564b20335cd289c1179f42a6c93d9b7487e35354f5
3
  size 5880