Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96a2846696aecb39c23a35fae16129ae08f32bd095f2db2c86287dcffe41075
+oid sha256:7af5479b06fda42d068e9925685ca16a9282c3b7881873822311e20c689b90b7
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ac23db58a17bb8e4c9a63365c6cc5a94d575b3778e55d15915be6129b09ff7
+oid sha256:7f347780b3bb8931c22c8b3c9eab71423276a10c62bb7baa8f0d7a3e337ae869
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1551c75b1334bcfe97e56752dd2a943a675ccb81f77b58ac2dcc098c9afc6ffb
+oid sha256:b60dc052bc8d38d9ba0fd9b6f183c42dfa2f7b5f7a63faeeb6d3a25338d58259
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.6,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 14.1,
       "eval_steps_per_second": 2.488,
       "step": 3
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.269885778427124,
+      "learning_rate": 6e-05,
+      "loss": 1.3039,
+      "step": 6
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.2148373126983643,
+      "eval_runtime": 1.2078,
+      "eval_samples_per_second": 14.075,
+      "eval_steps_per_second": 2.484,
+      "step": 6
     }
   ],
   "logging_steps": 3,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4265666056028160.0,
+  "total_flos": 8531332112056320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null