Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8caeeb6881c7936f987513e78daa19c5aec12ce0ceae2a30b0a04a8e4b8085cc
+oid sha256:48aa3685ad8b6ea63626e1b86b68d7d8c22a114d11bdf1ae962ac4d8772e4918
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894cd752b660ba539eaa1dc32f791d9d401f86cf0a983fd4b8ef41ca87370a38
+oid sha256:7931480ac71b52693036fbf4816bad532b8a6655783216f5b7f99ef27944157f
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258a74b0d1a7358be05d4768f42a506876926a0bdef94a1d7d492c6d84436515
+oid sha256:3afbbeff9c2106aa6747a9a6b6d1f2974325978cb30b288d183425c5cf2062c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6d88d0cff0a7882c1e9d832ad0060a624f8f63df9d77d6e8619b704896e700
+oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021114864864864864,
+  "epoch": 0.04222972972972973,
   "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": 3.931,
       "eval_steps_per_second": 1.969,
       "step": 25
+    },
+    {
+      "epoch": 0.02195945945945946,
+      "grad_norm": 3.3856303691864014,
+      "learning_rate": 0.0001848048096156426,
+      "loss": 0.3799,
+      "step": 26
+    },
+    {
+      "epoch": 0.022804054054054054,
+      "grad_norm": 4.26168966293335,
+      "learning_rate": 0.00018290375725550417,
+      "loss": 0.5836,
+      "step": 27
+    },
+    {
+      "epoch": 0.02364864864864865,
+      "grad_norm": 4.655025959014893,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6228,
+      "step": 28
+    },
+    {
+      "epoch": 0.024493243243243243,
+      "grad_norm": 5.267085075378418,
+      "learning_rate": 0.00017880107536067218,
+      "loss": 0.354,
+      "step": 29
+    },
+    {
+      "epoch": 0.02533783783783784,
+      "grad_norm": 3.4175171852111816,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.3025,
+      "step": 30
+    },
+    {
+      "epoch": 0.026182432432432432,
+      "grad_norm": 3.4233884811401367,
+      "learning_rate": 0.00017431448254773944,
+      "loss": 0.3893,
+      "step": 31
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 0.795799195766449,
+      "learning_rate": 0.0001719339800338651,
+      "loss": 0.0842,
+      "step": 32
+    },
+    {
+      "epoch": 0.02787162162162162,
+      "grad_norm": 2.771843671798706,
+      "learning_rate": 0.00016946583704589973,
+      "loss": 0.5852,
+      "step": 33
+    },
+    {
+      "epoch": 0.028716216216216218,
+      "grad_norm": 2.5016746520996094,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.467,
+      "step": 34
+    },
+    {
+      "epoch": 0.02956081081081081,
+      "grad_norm": 3.512495994567871,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.1078,
+      "step": 35
+    },
+    {
+      "epoch": 0.030405405405405407,
+      "grad_norm": 2.59957218170166,
+      "learning_rate": 0.0001615661475325658,
+      "loss": 0.2617,
+      "step": 36
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 1.0484542846679688,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0766,
+      "step": 37
+    },
+    {
+      "epoch": 0.03209459459459459,
+      "grad_norm": 12.746214866638184,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 0.3286,
+      "step": 38
+    },
+    {
+      "epoch": 0.032939189189189186,
+      "grad_norm": 0.457368403673172,
+      "learning_rate": 0.0001529919264233205,
+      "loss": 0.0239,
+      "step": 39
+    },
+    {
+      "epoch": 0.033783783783783786,
+      "grad_norm": 4.603786945343018,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2592,
+      "step": 40
+    },
+    {
+      "epoch": 0.03462837837837838,
+      "grad_norm": 4.357280731201172,
+      "learning_rate": 0.00014694715627858908,
+      "loss": 0.3277,
+      "step": 41
+    },
+    {
+      "epoch": 0.03547297297297297,
+      "grad_norm": 5.606065273284912,
+      "learning_rate": 0.00014383711467890774,
+      "loss": 0.9881,
+      "step": 42
+    },
+    {
+      "epoch": 0.036317567567567564,
+      "grad_norm": 0.958200216293335,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 0.0339,
+      "step": 43
+    },
+    {
+      "epoch": 0.037162162162162164,
+      "grad_norm": 0.9110239744186401,
+      "learning_rate": 0.00013746065934159123,
+      "loss": 0.0388,
+      "step": 44
+    },
+    {
+      "epoch": 0.03800675675675676,
+      "grad_norm": 10.007410049438477,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.1342,
+      "step": 45
+    },
+    {
+      "epoch": 0.03885135135135135,
+      "grad_norm": 3.0555267333984375,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1913,
+      "step": 46
+    },
+    {
+      "epoch": 0.03969594594594594,
+      "grad_norm": 4.296360969543457,
+      "learning_rate": 0.0001275637355816999,
+      "loss": 0.2431,
+      "step": 47
+    },
+    {
+      "epoch": 0.04054054054054054,
+      "grad_norm": 0.9275014400482178,
+      "learning_rate": 0.00012419218955996676,
+      "loss": 0.0389,
+      "step": 48
+    },
+    {
+      "epoch": 0.041385135135135136,
+      "grad_norm": 0.2515358626842499,
+      "learning_rate": 0.00012079116908177593,
+      "loss": 0.0064,
+      "step": 49
+    },
+    {
+      "epoch": 0.04222972972972973,
+      "grad_norm": 0.12618118524551392,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.0036,
+      "step": 50
+    },
+    {
+      "epoch": 0.04222972972972973,
+      "eval_loss": 0.24848654866218567,
+      "eval_runtime": 127.0152,
+      "eval_samples_per_second": 3.929,
+      "eval_steps_per_second": 1.968,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3054705844224e+16,
+  "total_flos": 6.6109411688448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null