Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8256081eb1fc3ee58336c5f8e829bdfdc8faccb0f8b0c05fbf93795f8b4e951d
+oid sha256:909b083afcbdfc3382c1b7c8320875f3f64ad0a3ff31fea68e544590814501c9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ceaea650a37fc36a9d9187bd1df2ad6476fbee90af547396205eff1a0eba8be
+oid sha256:b4b61e5ddab0bc1de7716bba07aad768398dc4c0221373cf9bcf1b349ea85a7f
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49211b7fe142805fa69f76b3d26aa3058bfa1004ebf0a1e824661dc6806f34a3
+oid sha256:9e3093311cde9ca58b8a5ff2c5cb16f96d74bc8f909add43bd289243be11a0e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04102096627164995,
+  "epoch": 0.049225159525979945,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 4.523,
       "eval_steps_per_second": 0.565,
       "step": 45
+    },
+    {
+      "epoch": 0.04375569735642662,
+      "grad_norm": 10.599452018737793,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 4.073,
+      "step": 48
+    },
+    {
+      "epoch": 0.04649042844120328,
+      "grad_norm": 8.252169609069824,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 4.3738,
+      "step": 51
+    },
+    {
+      "epoch": 0.049225159525979945,
+      "grad_norm": 10.953838348388672,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.5531,
+      "step": 54
+    },
+    {
+      "epoch": 0.049225159525979945,
+      "eval_loss": 0.9935899972915649,
+      "eval_runtime": 408.5367,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.565,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1847732052780646e+17,
+  "total_flos": 1.4273528823231283e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null