Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f39e02eb3974351950d28534c921f5196ca1b043c8270f47d8209bfef2389c6e
+oid sha256:a209e370e38f3052bdd0d1c0b95cffa543d516cd6ff63e179a34faf1a7d72856
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c96d91c7084fdcb7f626c9f024af93d73aba63e30ee01416bff004bcac741d8
+oid sha256:bbeb4a3d6dd3f91a772b3dfc5bab2bb51f4181339b77e46840bf6d7daa16ce58
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40337e495d1219cb3d2e8594d3017fd597c4ba51cb0f0b5fe566fc1e74f6a899
+oid sha256:aec5181e301b8d6c2defe02153441789f53ce857a83686acd097b751481655bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014988758431176618,
+  "epoch": 0.029977516862353237,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 6.171,
       "eval_steps_per_second": 3.085,
       "step": 15
+    },
+    {
+      "epoch": 0.017986510117411942,
+      "grad_norm": 11.424886703491211,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 9.8557,
+      "step": 18
+    },
+    {
+      "epoch": 0.019985011241568824,
+      "eval_loss": 2.4205539226531982,
+      "eval_runtime": 68.3769,
+      "eval_samples_per_second": 6.172,
+      "eval_steps_per_second": 3.086,
+      "step": 20
+    },
+    {
+      "epoch": 0.020984261803647264,
+      "grad_norm": 8.283842086791992,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.0089,
+      "step": 21
+    },
+    {
+      "epoch": 0.02398201348988259,
+      "grad_norm": 7.126759052276611,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 9.5498,
+      "step": 24
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "eval_loss": 2.336460828781128,
+      "eval_runtime": 68.4077,
+      "eval_samples_per_second": 6.169,
+      "eval_steps_per_second": 3.084,
+      "step": 25
+    },
+    {
+      "epoch": 0.02697976517611791,
+      "grad_norm": 6.901173114776611,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.1393,
+      "step": 27
+    },
+    {
+      "epoch": 0.029977516862353237,
+      "grad_norm": 5.120573043823242,
+      "learning_rate": 0.0,
+      "loss": 9.0794,
+      "step": 30
+    },
+    {
+      "epoch": 0.029977516862353237,
+      "eval_loss": 2.3162906169891357,
+      "eval_runtime": 68.4267,
+      "eval_samples_per_second": 6.167,
+      "eval_steps_per_second": 3.084,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9521744943513600.0,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null