madhuHuggingface commited on
Commit
a0a5369
·
verified ·
1 Parent(s): 6f58960

Training in progress, step 4700

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6400a6a5318992df1b0a0308f97a53a218096b7f6093df3d656dea048eec496
3
  size 121537408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302c1322c35281f55fe16dda8bc509e3dc7623639b3c33a1ebc8c40914369ca5
3
  size 121537408
last-checkpoint/adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "o_proj",
37
  "k_proj",
38
- "q_proj",
39
- "up_proj",
40
- "down_proj",
41
  "v_proj",
42
- "gate_proj"
 
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
 
36
  "k_proj",
37
+ "o_proj",
 
 
38
  "v_proj",
39
+ "gate_proj",
40
+ "down_proj",
41
+ "up_proj",
42
+ "q_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6400a6a5318992df1b0a0308f97a53a218096b7f6093df3d656dea048eec496
3
  size 121537408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aacd25a4e05082842ad71d0107cf487aace9bac3273148f257235c3fedfb2e5e
3
  size 121537408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536b0caf468c3b2f0e97609467859ae7a9095ccc477ce962ddf1561074342a50
3
  size 62000725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27cafe83e00a5eabc314cc5122b14622739544afd699f319c02ec341b5a0ab9f
3
  size 62000725
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7644dfc8daf6d079d14b00f67248c13208c962d589d1b867e182a9495b86cd9d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6205bb81b2e8389ef08b4f53f6908b25ff116635d540174f271ec2b2516e7cd7
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 2.869890795631825,
6
  "eval_steps": 500,
7
- "global_step": 4600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3228,6 +3228,146 @@
3228
  "learning_rate": 9.473963834676136e-07,
3229
  "loss": 0.0043,
3230
  "step": 4600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3231
  }
3232
  ],
3233
  "logging_steps": 10,
@@ -3242,12 +3382,12 @@
3242
  "should_evaluate": false,
3243
  "should_log": false,
3244
  "should_save": true,
3245
- "should_training_stop": false
3246
  },
3247
  "attributes": {}
3248
  }
3249
  },
3250
- "total_flos": 3.719326370781696e+16,
3251
  "train_batch_size": 2,
3252
  "trial_name": null,
3253
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
  "eval_steps": 500,
7
+ "global_step": 4809,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3228
  "learning_rate": 9.473963834676136e-07,
3229
  "loss": 0.0043,
3230
  "step": 4600
3231
+ },
3232
+ {
3233
+ "epoch": 2.8761310452418094,
3234
+ "grad_norm": 0.0513504222035408,
3235
+ "learning_rate": 8.594428422601608e-07,
3236
+ "loss": 0.004,
3237
+ "step": 4610
3238
+ },
3239
+ {
3240
+ "epoch": 2.882371294851794,
3241
+ "grad_norm": 0.0008744900114834309,
3242
+ "learning_rate": 7.757556843370428e-07,
3243
+ "loss": 0.002,
3244
+ "step": 4620
3245
+ },
3246
+ {
3247
+ "epoch": 2.8886115444617784,
3248
+ "grad_norm": 0.0013541991356760263,
3249
+ "learning_rate": 6.963385110648313e-07,
3250
+ "loss": 0.0021,
3251
+ "step": 4630
3252
+ },
3253
+ {
3254
+ "epoch": 2.894851794071763,
3255
+ "grad_norm": 0.04980359971523285,
3256
+ "learning_rate": 6.211947400569962e-07,
3257
+ "loss": 0.0025,
3258
+ "step": 4640
3259
+ },
3260
+ {
3261
+ "epoch": 2.9010920436817473,
3262
+ "grad_norm": 0.003807028057053685,
3263
+ "learning_rate": 5.503276050267458e-07,
3264
+ "loss": 0.0026,
3265
+ "step": 4650
3266
+ },
3267
+ {
3268
+ "epoch": 2.9073322932917316,
3269
+ "grad_norm": 0.10594616085290909,
3270
+ "learning_rate": 4.837401556478493e-07,
3271
+ "loss": 0.0055,
3272
+ "step": 4660
3273
+ },
3274
+ {
3275
+ "epoch": 2.913572542901716,
3276
+ "grad_norm": 0.000727578008081764,
3277
+ "learning_rate": 4.214352574235081e-07,
3278
+ "loss": 0.0042,
3279
+ "step": 4670
3280
+ },
3281
+ {
3282
+ "epoch": 2.9198127925117006,
3283
+ "grad_norm": 0.0013031769776716828,
3284
+ "learning_rate": 3.634155915629323e-07,
3285
+ "loss": 0.0037,
3286
+ "step": 4680
3287
+ },
3288
+ {
3289
+ "epoch": 2.926053042121685,
3290
+ "grad_norm": 0.002906072186306119,
3291
+ "learning_rate": 3.09683654866022e-07,
3292
+ "loss": 0.0018,
3293
+ "step": 4690
3294
+ },
3295
+ {
3296
+ "epoch": 2.9322932917316695,
3297
+ "grad_norm": 0.05608970671892166,
3298
+ "learning_rate": 2.602417596158868e-07,
3299
+ "loss": 0.0035,
3300
+ "step": 4700
3301
+ },
3302
+ {
3303
+ "epoch": 2.938533541341654,
3304
+ "grad_norm": 0.0014681172324344516,
3305
+ "learning_rate": 2.1509203347936934e-07,
3306
+ "loss": 0.005,
3307
+ "step": 4710
3308
+ },
3309
+ {
3310
+ "epoch": 2.944773790951638,
3311
+ "grad_norm": 0.1732673943042755,
3312
+ "learning_rate": 1.7423641941546332e-07,
3313
+ "loss": 0.003,
3314
+ "step": 4720
3315
+ },
3316
+ {
3317
+ "epoch": 2.9510140405616223,
3318
+ "grad_norm": 0.0007420650799758732,
3319
+ "learning_rate": 1.376766755916914e-07,
3320
+ "loss": 0.0036,
3321
+ "step": 4730
3322
+ },
3323
+ {
3324
+ "epoch": 2.957254290171607,
3325
+ "grad_norm": 0.0006529244128614664,
3326
+ "learning_rate": 1.0541437530848796e-07,
3327
+ "loss": 0.0035,
3328
+ "step": 4740
3329
+ },
3330
+ {
3331
+ "epoch": 2.9634945397815913,
3332
+ "grad_norm": 0.0012812407221645117,
3333
+ "learning_rate": 7.745090693143108e-08,
3334
+ "loss": 0.0028,
3335
+ "step": 4750
3336
+ },
3337
+ {
3338
+ "epoch": 2.9697347893915755,
3339
+ "grad_norm": 0.0007352688116952777,
3340
+ "learning_rate": 5.378747383154581e-08,
3341
+ "loss": 0.0024,
3342
+ "step": 4760
3343
+ },
3344
+ {
3345
+ "epoch": 2.9759750390015602,
3346
+ "grad_norm": 0.0036806329153478146,
3347
+ "learning_rate": 3.442509433352337e-08,
3348
+ "loss": 0.0027,
3349
+ "step": 4770
3350
+ },
3351
+ {
3352
+ "epoch": 2.9822152886115445,
3353
+ "grad_norm": 0.0006891420343890786,
3354
+ "learning_rate": 1.9364601671845173e-08,
3355
+ "loss": 0.0031,
3356
+ "step": 4780
3357
+ },
3358
+ {
3359
+ "epoch": 2.9884555382215288,
3360
+ "grad_norm": 0.062437161803245544,
3361
+ "learning_rate": 8.606643954978122e-09,
3362
+ "loss": 0.0034,
3363
+ "step": 4790
3364
+ },
3365
+ {
3366
+ "epoch": 2.994695787831513,
3367
+ "grad_norm": 0.12944412231445312,
3368
+ "learning_rate": 2.1516841374635834e-09,
3369
+ "loss": 0.0038,
3370
+ "step": 4800
3371
  }
3372
  ],
3373
  "logging_steps": 10,
 
3382
  "should_evaluate": false,
3383
  "should_log": false,
3384
  "should_save": true,
3385
+ "should_training_stop": true
3386
  },
3387
  "attributes": {}
3388
  }
3389
  },
3390
+ "total_flos": 3.887912126726554e+16,
3391
  "train_batch_size": 2,
3392
  "trial_name": null,
3393
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a915bc16632dcc1f89a12635ca0b186ecba95808935db991fa833a90741693e6
3
  size 6353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0554d7321c506bd816e992029d18cb4e33d99d8af5ebe99c62fa15c5a1cf0043
3
  size 6353