Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260a7f3a222986a8a1c4b4b4af984295c40dfdc8229c1dd37b8459df7420961c
+oid sha256:e4dcbc3ef5f8aa25a39835036502afb7614e5ed2a3cd32f3678d70ad93c35476
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36bd524b5f423471f1256f9d5a97610eccfe8b45ce85481fda9c1e46a6cd322b
+oid sha256:f8584acabe6c2caea85e93eacd5bff1e16eb8752d7c09639f9a8196bd06ef790
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8223884a837947fbfec558cb58e812c4074552a4c58d626bdabb079dd579f77a
+oid sha256:1b054ddbfa65831e80c01c0f7cfea7cb4b6060c7fa12bba539a0870629de1390
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00990916597853014,
+  "epoch": 0.010900082576383155,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 12.911,
       "eval_steps_per_second": 1.615,
       "step": 90
+    },
+    {
+      "epoch": 0.010239471511147812,
+      "grad_norm": 0.025197148323059082,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.0007,
+      "step": 93
+    },
+    {
+      "epoch": 0.010569777043765483,
+      "grad_norm": 10.560782432556152,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.0412,
+      "step": 96
+    },
+    {
+      "epoch": 0.010900082576383155,
+      "grad_norm": 0.04284638911485672,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.0004,
+      "step": 99
+    },
+    {
+      "epoch": 0.010900082576383155,
+      "eval_loss": 0.004690830130130053,
+      "eval_runtime": 1184.8269,
+      "eval_samples_per_second": 12.911,
+      "eval_steps_per_second": 1.615,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.350010183656407e+17,
+  "total_flos": 1.4906362444539494e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null