Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a7a0088decaaa5add76885b01276838eb760e8098ccc5e0a9af8b3818b81f2
+oid sha256:b7f97b2066eefeca8143bc65fc88fb4c2c35beb2a06e1a7759bac1ded73e81dd
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a11ebd4c974ca6d36521a8887a248ee267d1a7e0ac3eb82c5cb1e662191f21f
+oid sha256:09b208acf7d05b17425b68f447683784f074c6a56b4623aa38233115af065c62
 size 445914554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af60b2e5ead52adf8053bfc10d3b4749a58570429724f759d3d6fb65b4ea42c4
+oid sha256:b137d8fd1beeb694d07db804e60a00c6cbfd866066ae78c9d1c799e314281ee2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018971282221537148,
+  "epoch": 0.0028456923332305724,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 9.6165,
       "step": 18
+    },
+    {
+      "epoch": 0.0019919846332614004,
+      "grad_norm": 8.466657638549805,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.5539,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022765538665844576,
+      "grad_norm": 11.605523109436035,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.7119,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022765538665844576,
+      "eval_loss": 2.4811155796051025,
+      "eval_runtime": 517.5568,
+      "eval_samples_per_second": 8.577,
+      "eval_steps_per_second": 4.289,
+      "step": 24
+    },
+    {
+      "epoch": 0.002561123099907515,
+      "grad_norm": 8.81380844116211,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.0272,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028456923332305724,
+      "grad_norm": 8.043525695800781,
+      "learning_rate": 0.0,
+      "loss": 8.7699,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.361684987904e+16,
+  "total_flos": 2.042527481856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null