Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63498a2660f30b0a8c089ba171ebf547dfa7198092728a160419855d9a54285
+oid sha256:3d18355b73610ce0117af90f511f34cd12129e14a63abd3deee67f153508f406
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02067ea159020e6efe3a1f4a59871f44cf527be7da24b8514ccb07a5958e517f
+oid sha256:8b014d5ddeb01cfc7e54d5aabb38c2a2f1bf011ae92b0e154bafc4b95dc9bc16
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38de67135451dc9d085c3f7b16c13ead71106b6555c04a7ef9f50f76037e78c1
+oid sha256:c22c11b99d235cc38475fa1ebfdb7919352b0451c1412d19b7d8d73482a9b10d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457a0a52259cced6b76c949d89a7eea5b5ea9329c8fcb41a32547784be1dd99e
+oid sha256:3cd3f6e9267a2b7ffad41dddfa33b74e45aa7c480b8283eebbe1a013b2da49f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2727272727272725,
+  "epoch": 3.0,
   "eval_steps": 3,
-  "global_step": 25,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -254,6 +254,86 @@
       "learning_rate": 2.6996748113442394e-05,
       "loss": 2.7049,
       "step": 25
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.3256295323371887,
+      "learning_rate": 2.1165983894256647e-05,
+      "loss": 2.9422,
+      "step": 26
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.3431509733200073,
+      "learning_rate": 1.5872342839067306e-05,
+      "loss": 2.6983,
+      "step": 27
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "eval_loss": 1.3413066864013672,
+      "eval_runtime": 5.3602,
+      "eval_samples_per_second": 1.866,
+      "eval_steps_per_second": 0.373,
+      "step": 27
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.34741801023483276,
+      "learning_rate": 1.1214435464779006e-05,
+      "loss": 2.7043,
+      "step": 28
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.370277464389801,
+      "learning_rate": 7.2790297726755716e-06,
+      "loss": 2.5969,
+      "step": 29
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.39455196261405945,
+      "learning_rate": 4.139434924727359e-06,
+      "loss": 2.7283,
+      "step": 30
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_loss": 1.3317468166351318,
+      "eval_runtime": 5.3596,
+      "eval_samples_per_second": 1.866,
+      "eval_steps_per_second": 0.373,
+      "step": 30
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.4511341452598572,
+      "learning_rate": 1.8541356326100433e-06,
+      "loss": 2.5703,
+      "step": 31
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.3779066801071167,
+      "learning_rate": 4.6570269818346224e-07,
+      "loss": 2.6689,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.39674925804138184,
+      "learning_rate": 0.0,
+      "loss": 2.6383,
+      "step": 33
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3296959400177002,
+      "eval_runtime": 5.3524,
+      "eval_samples_per_second": 1.868,
+      "eval_steps_per_second": 0.374,
+      "step": 33
     }
   ],
   "logging_steps": 1,
@@ -268,12 +348,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.3478299623424e+16,
+  "total_flos": 8.379135550291968e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null