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:f38f5c6e438d8eb354e21dd173069df3195d88d28e1acc8dc8345ed809e08fd3
+oid sha256:76ee55eb50c694ed09f334f8d146a23525435e4554fa2d08012a2393ca964a27
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8030626cfd97239f74238d2d2b52e8191a791283c8f065ad65217752a566cf55
+oid sha256:81e2bfa32e13574a315a683815727a4e4dae391953e6651073f6e1072ee0ec09
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b4a47b0a2dec5f20b20056415034732099ef481b55693c7e57197106351f52
+oid sha256:97ca4e52a8ff86f0f650364416f5046b64a5370f50691b48fcfcc3c4dc51ebc4
 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": 0.13893713094824592,
+  "epoch": 0.2084056964223689,
   "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": 61.116,
       "eval_steps_per_second": 30.659,
       "step": 100
+    },
+    {
+      "epoch": 0.1528308440430705,
+      "grad_norm": 0.974806547164917,
+      "learning_rate": 0.0002,
+      "loss": 0.292,
+      "step": 110
+    },
+    {
+      "epoch": 0.1667245571378951,
+      "grad_norm": 0.9329864382743835,
+      "learning_rate": 0.0002,
+      "loss": 0.2803,
+      "step": 120
+    },
+    {
+      "epoch": 0.1806182702327197,
+      "grad_norm": 1.1351346969604492,
+      "learning_rate": 0.0002,
+      "loss": 0.2498,
+      "step": 130
+    },
+    {
+      "epoch": 0.1945119833275443,
+      "grad_norm": 0.8371953368186951,
+      "learning_rate": 0.0002,
+      "loss": 0.2312,
+      "step": 140
+    },
+    {
+      "epoch": 0.2084056964223689,
+      "grad_norm": 1.1801189184188843,
+      "learning_rate": 0.0002,
+      "loss": 0.2219,
+      "step": 150
+    },
+    {
+      "epoch": 0.2084056964223689,
+      "eval_loss": 0.256499707698822,
+      "eval_runtime": 4.9053,
+      "eval_samples_per_second": 61.769,
+      "eval_steps_per_second": 30.987,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 767238026035200.0,
+  "total_flos": 1150857039052800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null