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:d72bca9552ba49dd932f5372d2b40ec13b70727f256e4e714fc535998f8d2d7e
+oid sha256:e5be99f2c715494d365dee37c63636c97ea6e486b249dc0a2e612b81adca3166
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb509f5047a494859daa9945749de5275c99baf500d4ae87cc9d66f90df88ea
+oid sha256:5f19af37045281e1cefefdec91b2fab4c8ffd3409fbbbfffc87a3dda70eb7335
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c860bf3261aab67dc75a4cecd0fdeca58fd2c5dead9d0aa9d0d6b74d9d2e7b46
+oid sha256:a26453f066fae01af266c7691fba1ce619949626722b714291a766eae931e3c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3225806451612903,
+  "epoch": 0.3548387096774194,
   "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": 28.426,
       "eval_steps_per_second": 3.568,
       "step": 90
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.9477274417877197,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.6373,
+      "step": 93
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.910630464553833,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6084,
+      "step": 96
+    },
+    {
+      "epoch": 0.3548387096774194,
+      "grad_norm": 1.1343226432800293,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.7012,
+      "step": 99
+    },
+    {
+      "epoch": 0.3548387096774194,
+      "eval_loss": 0.5716129541397095,
+      "eval_runtime": 16.5377,
+      "eval_samples_per_second": 28.42,
+      "eval_steps_per_second": 3.568,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.690287047743898e+16,
+  "total_flos": 4.060859805676339e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null