Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096d0d1306c228ce8c01652e2e9dc22fbfdf66e56fe1c3cc3c3f3341baa59e44
+oid sha256:c4c6bb934a487e0bf0601fd224380c03ac2c0908fce3bd697d7a589d8505844a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43253be831e7ac99582443feb4b0497d91e5b08f1a4d38fec8bab185fced7dca
+oid sha256:519c4e0f8aaa133a54be4b7ffe0c982104341c51ad45e8055d3195783edc889c
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d0df08df7fd9b105c27325b0d737ee5dbb265a2a2aac9c9bc9fa9f7953db2d
+oid sha256:cbad8ba2c5033686167702b52f4d733e73fc51970594ffd4d36a57cb85a15e30
 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": 0.008108108108108109,
+  "epoch": 0.016216216216216217,
   "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": 3.266,
       "eval_steps_per_second": 3.266,
       "step": 3
+    },
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 0.25837552547454834,
+      "learning_rate": 8e-05,
+      "loss": 2.625,
+      "step": 4
+    },
+    {
+      "epoch": 0.013513513513513514,
+      "grad_norm": 0.3031831681728363,
+      "learning_rate": 0.0001,
+      "loss": 2.0932,
+      "step": 5
+    },
+    {
+      "epoch": 0.016216216216216217,
+      "grad_norm": 0.24016548693180084,
+      "learning_rate": 0.00012,
+      "loss": 2.3491,
+      "step": 6
+    },
+    {
+      "epoch": 0.016216216216216217,
+      "eval_loss": 2.193232774734497,
+      "eval_runtime": 23.9312,
+      "eval_samples_per_second": 3.259,
+      "eval_steps_per_second": 3.259,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1017260336480256.0,
+  "total_flos": 2034520672960512.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null