Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29641d0bbac95a39f7e20f68adef4f33e46ad91075e80207b525ce3a5fb74693
+oid sha256:428c9231fe186c1365c9b7fc3873df458324a246823aefd0ca2c26dcba8b405f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d69737c02da5771cb21474d7563fa6f5da86b166661e5bf633e46c9269a597
+oid sha256:b77f48a5a55cd337ef28c895370db01beb1202f104fc7fb72d0e185dd52a97ef
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4213eba836dc2866a95f6390ed6dbd9770a2bc1b9262f2a5ee50bdded503aa1f
+oid sha256:b503358a964c6a908a68122add090bad3de940062109847ca6e94a91812126b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03495145631067961,
+  "epoch": 0.03844660194174757,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 13.184,
       "eval_steps_per_second": 1.651,
       "step": 90
+    },
+    {
+      "epoch": 0.03611650485436893,
+      "grad_norm": 0.22146786749362946,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 2.0341,
+      "step": 93
+    },
+    {
+      "epoch": 0.037281553398058255,
+      "grad_norm": 0.19282077252864838,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 2.024,
+      "step": 96
+    },
+    {
+      "epoch": 0.03844660194174757,
+      "grad_norm": 0.2027566283941269,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 2.0638,
+      "step": 99
+    },
+    {
+      "epoch": 0.03844660194174757,
+      "eval_loss": 2.0377907752990723,
+      "eval_runtime": 328.107,
+      "eval_samples_per_second": 13.218,
+      "eval_steps_per_second": 1.655,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3463362391035085e+17,
+  "total_flos": 1.47704849532715e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null