Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9bbb2b8d7b7e3f403705c7d96e3721e4b36895b01e2ae40bb731b9163e2e71a
+oid sha256:efc165f98fe00876f13e8d514845dbfdaba88eeaf82051fcfe14fa93dc479758
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0981ce50f4950b1e2afae7eaa4777be331f62a3d14eabb87114fc403b17933
+oid sha256:41933031d745a105c06d494cef65225615bbbfb8a3e1ed1f2bdca4de159b1579
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abaa9373bbe156c59363a08f9fb6a81f0701ec05adf8ddebf0a95d11c5c0d35c
+oid sha256:4338e60828af3efb3dbfac479ffbce4cf22f201f32dd76c072dd2215e2af458f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028545941123996433,
+  "epoch": 0.057091882247992866,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 28.394,
       "eval_steps_per_second": 14.197,
       "step": 2
+    },
+    {
+      "epoch": 0.042818911685994644,
+      "grad_norm": 117.02621459960938,
+      "learning_rate": 3e-05,
+      "loss": 129.1238,
+      "step": 3
+    },
+    {
+      "epoch": 0.057091882247992866,
+      "grad_norm": 128.15509033203125,
+      "learning_rate": 4e-05,
+      "loss": 123.3496,
+      "step": 4
+    },
+    {
+      "epoch": 0.057091882247992866,
+      "eval_loss": 7.311307907104492,
+      "eval_runtime": 4.2522,
+      "eval_samples_per_second": 27.75,
+      "eval_steps_per_second": 13.875,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1302986508730368.0,
+  "total_flos": 2605973017460736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null