Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a919ab2299e2cea506182209e4da96877c35cf08f91e333b76a85db738356fe
+oid sha256:ab74057ae08d664fd9f25479207452cf9dbadb9cd5372a66eca63fb466be9044
 size 1673329784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f349802d55f333a5ba83727d452c80e7929fc058acd51c3880dbecff08243f85
+oid sha256:e159879577b8f21547d60e1882216c44621e4762dbd7b0aa6a29d473e15bc0c7
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a5e45a0438fbab713e625bf624a63eff4059dbc3b3e53c50c4901d44981284
+oid sha256:f63964d2edbcbf6dec0f05bec9d43e1b6a932832c56eac5659d289779cafe1e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023391812865497075,
+  "epoch": 0.04678362573099415,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 3.6788,
       "step": 5
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 95.90052795410156,
+      "learning_rate": 0.00012,
+      "loss": 3.0436,
+      "step": 6
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "eval_loss": 1.5273349285125732,
+      "eval_runtime": 37.7963,
+      "eval_samples_per_second": 2.381,
+      "eval_steps_per_second": 1.191,
+      "step": 6
+    },
+    {
+      "epoch": 0.03274853801169591,
+      "grad_norm": 47.590003967285156,
+      "learning_rate": 0.00014,
+      "loss": 1.344,
+      "step": 7
+    },
+    {
+      "epoch": 0.03742690058479532,
+      "grad_norm": 15.51590347290039,
+      "learning_rate": 0.00016,
+      "loss": 0.3831,
+      "step": 8
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 5.955617904663086,
+      "learning_rate": 0.00018,
+      "loss": 0.1707,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 0.19208240509033203,
+      "eval_runtime": 37.905,
+      "eval_samples_per_second": 2.374,
+      "eval_steps_per_second": 1.187,
+      "step": 9
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 2.474229574203491,
+      "learning_rate": 0.0002,
+      "loss": 0.095,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2794842929233920.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null