sambar commited on
Commit
b102876
1 Parent(s): 51cd282

Model save

Browse files
adapter_config.json CHANGED
@@ -17,9 +17,9 @@
17
  "revision": null,
18
  "target_modules": [
19
  "q_proj",
 
20
  "v_proj",
21
- "o_proj",
22
- "k_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "q_proj",
20
+ "k_proj",
21
  "v_proj",
22
+ "o_proj"
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab86371f50ae43ed266252d6db4b66c379eff8391b9543f7ed4782761a7432c
3
  size 218138576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86153f980d9b196097ccc204da082dd9c6aeafc01ef1aa0bfcc4790e74b9d4a9
3
  size 218138576
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 0.67,
3
- "eval_loss": 0.9899529814720154,
4
- "eval_runtime": 2915.5922,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 7.926,
7
- "eval_steps_per_second": 0.991,
8
- "train_loss": 1.009575615034384,
9
- "train_runtime": 87164.7513,
10
  "train_samples": 207865,
11
- "train_samples_per_second": 2.385,
12
  "train_steps_per_second": 0.005
13
  }
 
1
  {
2
  "epoch": 0.67,
3
+ "eval_loss": 0.9899672269821167,
4
+ "eval_runtime": 2925.3835,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 7.9,
7
+ "eval_steps_per_second": 0.988,
8
+ "train_loss": 1.0095806910711176,
9
+ "train_runtime": 87675.0459,
10
  "train_samples": 207865,
11
+ "train_samples_per_second": 2.371,
12
  "train_steps_per_second": 0.005
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.67,
3
- "eval_loss": 0.9899529814720154,
4
- "eval_runtime": 2915.5922,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 7.926,
7
- "eval_steps_per_second": 0.991
8
  }
 
1
  {
2
  "epoch": 0.67,
3
+ "eval_loss": 0.9899672269821167,
4
+ "eval_runtime": 2925.3835,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 7.9,
7
+ "eval_steps_per_second": 0.988
8
  }
runs/Dec30_09-43-19_node-0/events.out.tfevents.1703958425.node-0.3394.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14be31447647ea0e181f47e25465c386aba04be06ea492f559857aed329f2ad
3
+ size 13436
runs/Dec30_09-43-19_node-0/events.out.tfevents.1704049025.node-0.3394.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be60f08243dab2e724f736c541449536b880bc5177e8d8a9b4b9ec3fd399372b
3
+ size 359
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.67,
3
- "train_loss": 1.009575615034384,
4
- "train_runtime": 87164.7513,
5
  "train_samples": 207865,
6
- "train_samples_per_second": 2.385,
7
  "train_steps_per_second": 0.005
8
  }
 
1
  {
2
  "epoch": 0.67,
3
+ "train_loss": 1.0095806910711176,
4
+ "train_runtime": 87675.0459,
5
  "train_samples": 207865,
6
+ "train_samples_per_second": 2.371,
7
  "train_steps_per_second": 0.005
8
  }
trainer_state.json CHANGED
@@ -149,19 +149,19 @@
149
  {
150
  "epoch": 0.28,
151
  "learning_rate": 1.627812124672099e-05,
152
- "loss": 0.9937,
153
  "step": 115
154
  },
155
  {
156
  "epoch": 0.3,
157
  "learning_rate": 1.5971585917027864e-05,
158
- "loss": 0.998,
159
  "step": 120
160
  },
161
  {
162
  "epoch": 0.31,
163
  "learning_rate": 1.5656068754865388e-05,
164
- "loss": 0.9953,
165
  "step": 125
166
  },
167
  {
@@ -281,7 +281,7 @@
281
  {
282
  "epoch": 0.55,
283
  "learning_rate": 8.263518223330698e-06,
284
- "loss": 0.9917,
285
  "step": 225
286
  },
287
  {
@@ -305,7 +305,7 @@
305
  {
306
  "epoch": 0.6,
307
  "learning_rate": 6.762660579416791e-06,
308
- "loss": 0.9967,
309
  "step": 245
310
  },
311
  {
@@ -340,19 +340,19 @@
340
  },
341
  {
342
  "epoch": 0.67,
343
- "eval_loss": 0.9899529814720154,
344
- "eval_runtime": 2912.0163,
345
- "eval_samples_per_second": 7.936,
346
- "eval_steps_per_second": 0.992,
347
  "step": 272
348
  },
349
  {
350
  "epoch": 0.67,
351
  "step": 272,
352
  "total_flos": 1.2275875027210994e+19,
353
- "train_loss": 1.009575615034384,
354
- "train_runtime": 87164.7513,
355
- "train_samples_per_second": 2.385,
356
  "train_steps_per_second": 0.005
357
  }
358
  ],
 
149
  {
150
  "epoch": 0.28,
151
  "learning_rate": 1.627812124672099e-05,
152
+ "loss": 0.9936,
153
  "step": 115
154
  },
155
  {
156
  "epoch": 0.3,
157
  "learning_rate": 1.5971585917027864e-05,
158
+ "loss": 0.9981,
159
  "step": 120
160
  },
161
  {
162
  "epoch": 0.31,
163
  "learning_rate": 1.5656068754865388e-05,
164
+ "loss": 0.9954,
165
  "step": 125
166
  },
167
  {
 
281
  {
282
  "epoch": 0.55,
283
  "learning_rate": 8.263518223330698e-06,
284
+ "loss": 0.9918,
285
  "step": 225
286
  },
287
  {
 
305
  {
306
  "epoch": 0.6,
307
  "learning_rate": 6.762660579416791e-06,
308
+ "loss": 0.9968,
309
  "step": 245
310
  },
311
  {
 
340
  },
341
  {
342
  "epoch": 0.67,
343
+ "eval_loss": 0.9899672269821167,
344
+ "eval_runtime": 2926.0545,
345
+ "eval_samples_per_second": 7.898,
346
+ "eval_steps_per_second": 0.987,
347
  "step": 272
348
  },
349
  {
350
  "epoch": 0.67,
351
  "step": 272,
352
  "total_flos": 1.2275875027210994e+19,
353
+ "train_loss": 1.0095806910711176,
354
+ "train_runtime": 87675.0459,
355
+ "train_samples_per_second": 2.371,
356
  "train_steps_per_second": 0.005
357
  }
358
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7cb521cdf4c1fd969ef51bd2d60bbfa27ab215cc3c126b7930b1bf1876bbb81
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48012117f359d93f6f11e37307131da164e15c7f0c3130b3e312cd4922e74142
3
  size 4664