Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23977cd26c7c6987875981b203fc45dc0a03e1bce33f18166a3141eb070041c4
+oid sha256:11f37ef39944e005a0cdaaaf0880b73609ef29f3a56957e8b1d5fe7745487f25
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0141c72a860c1a8dee4d91b84075cd61710a5932dfbca835cb2cebda10b91e5
+oid sha256:8fb6b551666af67a667f6fed63048959a49575423b58556cc2b385d3e42cfb42
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05936d78f5fcce6d03f9ecabc1902ae587fa70e4e91f0b4774a5e89aa5602ac0
+oid sha256:a91963eadbc40670a98d15120d3356a5907c79c2001467d26be64e710331f4a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002128497387269457,
+  "epoch": 0.004256994774538914,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 133.312,
       "eval_steps_per_second": 66.663,
       "step": 25
+    },
+    {
+      "epoch": 0.0022136372827602354,
+      "grad_norm": 0.1304478943347931,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.3695,
+      "step": 26
+    },
+    {
+      "epoch": 0.002298777178251014,
+      "grad_norm": 0.1295875608921051,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3707,
+      "step": 27
+    },
+    {
+      "epoch": 0.002383917073741792,
+      "grad_norm": 0.11449471116065979,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.3833,
+      "step": 28
+    },
+    {
+      "epoch": 0.0024690569692325704,
+      "grad_norm": 0.1458948850631714,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.37,
+      "step": 29
+    },
+    {
+      "epoch": 0.0025541968647233484,
+      "grad_norm": 0.12886323034763336,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3815,
+      "step": 30
+    },
+    {
+      "epoch": 0.002639336760214127,
+      "grad_norm": 0.11445284634828568,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3738,
+      "step": 31
+    },
+    {
+      "epoch": 0.0027244766557049053,
+      "grad_norm": 0.12730805575847626,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.3677,
+      "step": 32
+    },
+    {
+      "epoch": 0.0028096165511956833,
+      "grad_norm": 0.175711527466774,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3789,
+      "step": 33
+    },
+    {
+      "epoch": 0.0028947564466864618,
+      "grad_norm": 0.1383206993341446,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 10.3737,
+      "step": 34
+    },
+    {
+      "epoch": 0.0029798963421772398,
+      "grad_norm": 0.14329196512699127,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3724,
+      "step": 35
+    },
+    {
+      "epoch": 0.0030650362376680182,
+      "grad_norm": 0.1304287165403366,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 10.3729,
+      "step": 36
+    },
+    {
+      "epoch": 0.0031501761331587967,
+      "grad_norm": 0.15487420558929443,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.3613,
+      "step": 37
+    },
+    {
+      "epoch": 0.0032353160286495747,
+      "grad_norm": 0.16208356618881226,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 10.3589,
+      "step": 38
+    },
+    {
+      "epoch": 0.003320455924140353,
+      "grad_norm": 0.16646641492843628,
+      "learning_rate": 5e-05,
+      "loss": 10.3753,
+      "step": 39
+    },
+    {
+      "epoch": 0.0034055958196311316,
+      "grad_norm": 0.1642124056816101,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 10.3586,
+      "step": 40
+    },
+    {
+      "epoch": 0.0034907357151219096,
+      "grad_norm": 0.16558325290679932,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.3625,
+      "step": 41
+    },
+    {
+      "epoch": 0.003575875610612688,
+      "grad_norm": 0.18477176129817963,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3724,
+      "step": 42
+    },
+    {
+      "epoch": 0.003661015506103466,
+      "grad_norm": 0.13750387728214264,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3534,
+      "step": 43
+    },
+    {
+      "epoch": 0.0037461554015942445,
+      "grad_norm": 0.15226051211357117,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.3561,
+      "step": 44
+    },
+    {
+      "epoch": 0.003831295297085023,
+      "grad_norm": 0.16481082141399384,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3705,
+      "step": 45
+    },
+    {
+      "epoch": 0.003916435192575801,
+      "grad_norm": 0.16374343633651733,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.3746,
+      "step": 46
+    },
+    {
+      "epoch": 0.0040015750880665795,
+      "grad_norm": 0.1810373067855835,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3756,
+      "step": 47
+    },
+    {
+      "epoch": 0.004086714983557358,
+      "grad_norm": 0.15905612707138062,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3727,
+      "step": 48
+    },
+    {
+      "epoch": 0.004171854879048136,
+      "grad_norm": 0.20548060536384583,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.374,
+      "step": 49
+    },
+    {
+      "epoch": 0.004256994774538914,
+      "grad_norm": 0.2801133990287781,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 10.3681,
+      "step": 50
+    },
+    {
+      "epoch": 0.004256994774538914,
+      "eval_loss": 10.362723350524902,
+      "eval_runtime": 74.015,
+      "eval_samples_per_second": 133.635,
+      "eval_steps_per_second": 66.824,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3060589264896.0,
+  "total_flos": 5733592989696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null