Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4f22c9a8eeee1ba500f6fd3bc6f0d41e02e20e42dd939e4bf3e86960f8cf24
+oid sha256:4dcb5a8425529190f218572317dcab771f74f976f053a33bc71aca0e2946c5b5
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a21a0e7696fde896805e2355601e1e3ba8f7d2b7f11cfbe869e7b6d628647b
+oid sha256:0931811f456074fdea1af0f0b742b3acb54b9d1d29b3240aa140cc260e35a553
 size 847674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b1d1c847833c161251571b388af565d36854d60391836c815a5c304e314a4b
+oid sha256:f89ee07fe03d1a05ba9f35a1ae7e0f887e7de2494b1948e33f324c76bd30d853
 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": 0.00014841382722156947,
+  "epoch": 0.00029682765444313895,
   "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": 178.443,
       "eval_steps_per_second": 89.232,
       "step": 3
+    },
+    {
+      "epoch": 0.00019788510296209265,
+      "grad_norm": 6.049842834472656,
+      "learning_rate": 8e-05,
+      "loss": 9.5229,
+      "step": 4
+    },
+    {
+      "epoch": 0.00024735637870261577,
+      "grad_norm": 6.059463024139404,
+      "learning_rate": 0.0001,
+      "loss": 9.6265,
+      "step": 5
+    },
+    {
+      "epoch": 0.00029682765444313895,
+      "grad_norm": 6.40576696395874,
+      "learning_rate": 0.00012,
+      "loss": 9.4738,
+      "step": 6
+    },
+    {
+      "epoch": 0.00029682765444313895,
+      "eval_loss": 9.306656837463379,
+      "eval_runtime": 47.9088,
+      "eval_samples_per_second": 177.65,
+      "eval_steps_per_second": 88.835,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 196675633152.0,
+  "total_flos": 393351266304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null