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:c97a6eb7828ab12bf99a84c4cf9a85255ac44fd2308fcd126b57889dd4265fb5
+oid sha256:e427f4975007f1fca6bace65a5c0c7a6797abf55321e242de509d73ad766d1e0
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f19e537b18c2e0ef84ad64b6d67f53fad8c31b4ead4b80caeedc82fdb948ef
+oid sha256:38bef9ab7c5d2a5e0825f7cab2bcef109780dc3b94a081bb10a56d654d977ff7
 size 83372758

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94da6e3366f129f25133426e3c63c9070e4de201dd82e44019bab20f58ea2c12
+oid sha256:fd13790505a93df46a8768a128b3bb67ce84c51c104ba912c827459ad85e7d7e
 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": 0.014781966001478197,
+  "epoch": 0.029563932002956393,
   "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": 9.262,
       "eval_steps_per_second": 4.631,
       "step": 15
+    },
+    {
+      "epoch": 0.017738359201773836,
+      "grad_norm": 0.7007733583450317,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4142,
+      "step": 18
+    },
+    {
+      "epoch": 0.01970928800197093,
+      "eval_loss": 1.4901186227798462,
+      "eval_runtime": 46.1925,
+      "eval_samples_per_second": 9.266,
+      "eval_steps_per_second": 4.633,
+      "step": 20
+    },
+    {
+      "epoch": 0.020694752402069475,
+      "grad_norm": 0.7448059320449829,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.6253,
+      "step": 21
+    },
+    {
+      "epoch": 0.023651145602365115,
+      "grad_norm": 0.6697611212730408,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.4523,
+      "step": 24
+    },
+    {
+      "epoch": 0.02463661000246366,
+      "eval_loss": 1.4631699323654175,
+      "eval_runtime": 46.1947,
+      "eval_samples_per_second": 9.265,
+      "eval_steps_per_second": 4.633,
+      "step": 25
+    },
+    {
+      "epoch": 0.026607538802660754,
+      "grad_norm": 0.6793627142906189,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.495,
+      "step": 27
+    },
+    {
+      "epoch": 0.029563932002956393,
+      "grad_norm": 0.6140923500061035,
+      "learning_rate": 0.0,
+      "loss": 1.3848,
+      "step": 30
+    },
+    {
+      "epoch": 0.029563932002956393,
+      "eval_loss": 1.456243872642517,
+      "eval_runtime": 46.1815,
+      "eval_samples_per_second": 9.268,
+      "eval_steps_per_second": 4.634,
+      "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": 2800545051967488.0,
+  "total_flos": 5551080370864128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null