Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db481b07f42c039d03e89eea595270b0faf4fc22f676af84347f1115f1fb4834
+oid sha256:e0d54388443ec393e4174e0ff722e73d9f16bbc15628918fc5a5f7379ad1b1c3
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda5230c546934ca1b67146e31a5b6caeeff196c4cd24b7c492a71e7141e9c0a
+oid sha256:2cadda56dab8914de7a54dbe8684ee28f2fc8c54b0c8305541b34eafef991e48
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c900d4c6853d677a7868b2838751ed164390e83255a80643445dc284e68bad62
+oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007669446841146582,
+  "epoch": 0.011504170261719874,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 335.776,
       "eval_steps_per_second": 167.888,
       "step": 100
+    },
+    {
+      "epoch": 0.00843639152526124,
+      "grad_norm": 0.1241370439529419,
+      "learning_rate": 0.0002,
+      "loss": 10.3313,
+      "step": 110
+    },
+    {
+      "epoch": 0.009203336209375898,
+      "grad_norm": 0.1485566943883896,
+      "learning_rate": 0.0002,
+      "loss": 10.3256,
+      "step": 120
+    },
+    {
+      "epoch": 0.009970280893490557,
+      "grad_norm": 0.1361122876405716,
+      "learning_rate": 0.0002,
+      "loss": 10.3242,
+      "step": 130
+    },
+    {
+      "epoch": 0.010737225577605215,
+      "grad_norm": 0.1488087922334671,
+      "learning_rate": 0.0002,
+      "loss": 10.3233,
+      "step": 140
+    },
+    {
+      "epoch": 0.011504170261719874,
+      "grad_norm": 0.1264934092760086,
+      "learning_rate": 0.0002,
+      "loss": 10.323,
+      "step": 150
+    },
+    {
+      "epoch": 0.011504170261719874,
+      "eval_loss": 10.316740989685059,
+      "eval_runtime": 16.298,
+      "eval_samples_per_second": 336.852,
+      "eval_steps_per_second": 168.426,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2440708915200.0,
+  "total_flos": 3685308825600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null