Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:281e89a2076b06545dc7b205d0a8539ac4097c7417d40575850053f7b58ec4ae
+oid sha256:e4207b5deb6b8638400939fd922abfb7c33ce64d091e3d923c5a3a079cf08e50
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c4da42ab390b195121001bad5b51a0b3f33c293691a8a7d0f6bdc561a60740
+oid sha256:53468b5d6dd709a560722ea73e3c1c3d8389384e72850e1001ab968e17552f68
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0057306590257879654,
+  "epoch": 0.011461318051575931,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 17.083,
       "eval_steps_per_second": 8.58,
       "step": 3
+    },
+    {
+      "epoch": 0.007640878701050621,
+      "grad_norm": 1.2270911931991577,
+      "learning_rate": 8e-05,
+      "loss": 3.0984,
+      "step": 4
+    },
+    {
+      "epoch": 0.009551098376313277,
+      "grad_norm": 1.2903715372085571,
+      "learning_rate": 0.0001,
+      "loss": 2.8426,
+      "step": 5
+    },
+    {
+      "epoch": 0.011461318051575931,
+      "grad_norm": 1.04902982711792,
+      "learning_rate": 0.00012,
+      "loss": 3.102,
+      "step": 6
+    },
+    {
+      "epoch": 0.011461318051575931,
+      "eval_loss": 2.867784023284912,
+      "eval_runtime": 12.9552,
+      "eval_samples_per_second": 17.059,
+      "eval_steps_per_second": 8.568,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 2219477097775104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null