Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2197f08b4c4c75d4765914df02d5bee5d1df7a00b0a5d54d22d5f145674d9613
+oid sha256:53eb728a2747d5a2d00c78ade1a8de88b47e0ac617f7fe6ea393ae6d21b8625b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a7835342e9e035c0aab112afbd6ee6fd0975cd0de9525e9f7746f70ff9e8f7
+oid sha256:20f4f535b97267baea0c8efa9482b0bd502b46479a1c759bbdedecbf2bda2741
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d6c6954105413e254c1dc776a27dd427206924cc5f1ee48db29b4f18851c42
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 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": 0.0012352541535420912,
+  "epoch": 0.0024705083070841825,
   "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": 11.687,
       "eval_steps_per_second": 5.844,
       "step": 15
+    },
+    {
+      "epoch": 0.0014823049842505095,
+      "grad_norm": 8.56024169921875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.9031,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016470055380561218,
+      "eval_loss": 3.1714038848876953,
+      "eval_runtime": 437.5581,
+      "eval_samples_per_second": 11.685,
+      "eval_steps_per_second": 5.844,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017293558149589277,
+      "grad_norm": 6.161643028259277,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.526,
+      "step": 21
+    },
+    {
+      "epoch": 0.001976406645667346,
+      "grad_norm": 1.7391244173049927,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.3455,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020587569225701523,
+      "eval_loss": 3.113889455795288,
+      "eval_runtime": 437.6166,
+      "eval_samples_per_second": 11.684,
+      "eval_steps_per_second": 5.843,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022234574763757642,
+      "grad_norm": 3.226254940032959,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.9946,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024705083070841825,
+      "grad_norm": 1.8411797285079956,
+      "learning_rate": 0.0,
+      "loss": 2.8344,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024705083070841825,
+      "eval_loss": 3.099670171737671,
+      "eval_runtime": 437.5735,
+      "eval_samples_per_second": 11.685,
+      "eval_steps_per_second": 5.844,
+      "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": 5564154626703360.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null