Training in progress, epoch 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd31912d2e7456ca9ee494065be293de05a284a6a89a1fbda0901c0383eff275
+oid sha256:5ba61d1259d3a166794e85bf13638446970059851ee9d372affb1e473f2809a8
 size 146815928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d943502409a489b96330ea2c48f1d4c175ab07e43eb0fd8bec333a0940ec58
+oid sha256:b8f24799c769ec928c84290e0f7676a0ed8f6c5c46215c2de29c869d7d34e5e5
 size 74680890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfefd6aee112404b8dfd1d4e102649092133b68dba1f16d7943106005276a5b
+oid sha256:cd028caa5142b17a0b8979386893f3c02081255179b70983a3b19232b3b5706a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984a934e6ad2a5d5b45a64fb9146b00851b3de0b43de3949c78ce5b1be89d2de
+oid sha256:5aa4bcc8a211b0b4d0d438488c7be8218bdc07991923d557342d812a16a0576f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2450,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,42 @@
       "eval_samples_per_second": 2.11,
       "eval_steps_per_second": 0.528,
       "step": 2450
+    },
+    {
+      "epoch": 7.142857142857143,
+      "grad_norm": 0.4159909188747406,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.1573,
+      "step": 2500
+    },
+    {
+      "epoch": 7.428571428571429,
+      "grad_norm": 0.32118484377861023,
+      "learning_rate": 6e-05,
+      "loss": 0.1458,
+      "step": 2600
+    },
+    {
+      "epoch": 7.714285714285714,
+      "grad_norm": 0.46313735842704773,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.1503,
+      "step": 2700
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.41984930634498596,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.1527,
+      "step": 2800
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.24533726274967194,
+      "eval_runtime": 331.7124,
+      "eval_samples_per_second": 2.11,
+      "eval_steps_per_second": 0.528,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
@@ -250,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.004958226808832e+16,
+  "total_flos": 6.862976795541504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null