Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9f18bd940d1ca3ba7749630e1919c362336ace9fa4f754d422b3449ca6d938
+oid sha256:2dfa40714ee9d3ed193d0cbb0d5f2f06ed44f4d4b6b02e102420a29642c6d11a
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957506baa1c8b9696353dcc790bc4130b347b3caa081a970a6b9d70718e50c45
+oid sha256:2608188f277c9390a0d5edb97ab20985d2cac1fc364523b1b5aaf1781d3c6ff3
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8586512a4566a393800b83e344d6730e6751cb11be4ad93fd9de02ed9e47b01f
+oid sha256:fbe38599c452d9ae6dc34f6e1fc26d8c070f9321d6d7b5ad8731beaf1827578f
 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": 0.014492753623188406,
+  "epoch": 0.028985507246376812,
   "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": 57.619,
       "eval_steps_per_second": 28.81,
       "step": 3
+    },
+    {
+      "epoch": 0.01932367149758454,
+      "grad_norm": 4.04183292388916,
+      "learning_rate": 8e-05,
+      "loss": 44.3261,
+      "step": 4
+    },
+    {
+      "epoch": 0.024154589371980676,
+      "grad_norm": 4.250118255615234,
+      "learning_rate": 0.0001,
+      "loss": 44.298,
+      "step": 5
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 3.9748477935791016,
+      "learning_rate": 0.00012,
+      "loss": 44.2598,
+      "step": 6
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "eval_loss": 11.053829193115234,
+      "eval_runtime": 1.5763,
+      "eval_samples_per_second": 55.828,
+      "eval_steps_per_second": 27.914,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 249594642432.0,
+  "total_flos": 499189284864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null