Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eea7b7d5b8d2cbcb2ef68668338e2e9ecc217c7f365a2af0425ba30975c7616
+oid sha256:5d7b7a0da61877e28c87cc4ffd9f2e9dfaf8830874125edd72e4be83b1223073
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92f8186efe02db2fba643c135e1ff2a24db67c836b640734a581b8e8a00e654
+oid sha256:996282b583a294e344d85f611821584bb03426ac5932218086b3b12f57604192
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179c15906d11e20b943dedfcd9cf2ecdec4ee0e5b0cb6f89d9231b21dbe986a0
+oid sha256:16ae7958aba3908f89853844262201daac04359d589f99dfb497f6e44d009b6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef0e768220ab06b0b8ca60bf0cb82c3ba1ffa61503120e1cf6e3622be29cf83
+oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07069219440353461,
+  "epoch": 0.09425625920471281,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 3.917,
       "eval_steps_per_second": 1.961,
       "step": 30
+    },
+    {
+      "epoch": 0.09425625920471281,
+      "grad_norm": 21.754932403564453,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 17.9564,
+      "step": 40
+    },
+    {
+      "epoch": 0.09425625920471281,
+      "eval_loss": 1.1547653675079346,
+      "eval_runtime": 181.1181,
+      "eval_samples_per_second": 3.948,
+      "eval_steps_per_second": 1.977,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9970653339713536e+16,
+  "total_flos": 3.974178739637453e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null