Training in progress, epoch 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca016f972ff2ad4f3bf690d810f748cd5d17582390326ca08c105b8f17981d63
+oid sha256:ff18b78e9495eae88b2aab80580e8790c2ea74fcf4f7e6484bbe2c870e56a8b7
 size 146815928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c1e0c5fb7fec933dc4f450340813b9173fd47c38dc7bd03b8fd54ae634afbe
+oid sha256:3cf32c52d73832147adfeeee41ff7c6ea6e0dc6cc369b204ac04c55f6a3a72e3
 size 74680890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b74f6db6173db8ce9081542b2c273335304d77891e1c11d131f4f4b5df6066
+oid sha256:99a75ce073a6c74625ca2933c59efc2bbdec73e4dcc9c0f42c6635108770fd0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3ee03ba61886e9f659b6b5747d35d37da569234d10d7c1f12931685c580c5c
+oid sha256:4c993e8ee8af283924df8f63ed21f3efad8f3c9d9bc2b9b16c0d84b0dff0ef93
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 1050,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,42 @@
       "eval_samples_per_second": 2.11,
       "eval_steps_per_second": 0.527,
       "step": 1050
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.3725013732910156,
+      "learning_rate": 0.00016,
+      "loss": 0.2173,
+      "step": 1100
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.3499898612499237,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.216,
+      "step": 1200
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.369825541973114,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.2049,
+      "step": 1300
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.28506389260292053,
+      "learning_rate": 0.00014,
+      "loss": 0.2089,
+      "step": 1400
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.24056243896484375,
+      "eval_runtime": 331.7171,
+      "eval_samples_per_second": 2.11,
+      "eval_steps_per_second": 0.528,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -120,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.569868529159373e+16,
+  "total_flos": 3.435572847915827e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null