Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6176fcd9ff5767ba145007fefdcbf7fab75e7150d5ab5328d586d3a1d1ca08c4
+oid sha256:97a742c5c008a4bb04d731942ecfee4c1109062b5ee267fee7fee0f7a08054b1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563f5a53921b6394c99152b4858a22a6cfc8d034348c5e37bb0c890a48b9c70f
+oid sha256:cb28265179b220a69fd9689dca9c54ae06e8a4dda428c017537402b1db4aa46e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f15464d6b0aa5ccf50fef2eb140dcf3fae680aa29c7705ea6dfce2709e29b1
+oid sha256:3eee6eae3b8186ef126160899f88aa5d837d5e4baeb214aac70c66bbeb9a29a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf140526b08395dbd0793ca343f0f70c5fb866a714c27208d9b9b1ce1a60172
+oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016816816816816817,
+  "epoch": 0.025225225225225224,
   "eval_steps": 14,
-  "global_step": 28,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,28 @@
       "eval_samples_per_second": 30.457,
       "eval_steps_per_second": 15.25,
       "step": 28
+    },
+    {
+      "epoch": 0.018018018018018018,
+      "grad_norm": 2.959623336791992,
+      "learning_rate": 0.0001,
+      "loss": 1.0187,
+      "step": 30
+    },
+    {
+      "epoch": 0.024024024024024024,
+      "grad_norm": 4.844839096069336,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.7602,
+      "step": 40
+    },
+    {
+      "epoch": 0.025225225225225224,
+      "eval_loss": 0.1556524932384491,
+      "eval_runtime": 22.9916,
+      "eval_samples_per_second": 30.489,
+      "eval_steps_per_second": 15.266,
+      "step": 42
     }
   ],
   "logging_steps": 10,
@@ -64,7 +86,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4560497877712896.0,
+  "total_flos": 6840746816569344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null