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:bb66c9abc7746f2f626a7d6484e9521532b62a02d4da2d6d414818ce86401b01
+oid sha256:a8526857e439ccded547faf4e04e6c50bd16b2abe44c011ad06191a88d94c930
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c150d6c207a76db4e48de6a91262263dcba21e086b0c05e77a027d5ba7007077
+oid sha256:e3583d7424ca89f63255c5e695b9b9810c7e82d1e13771761e058e0c2432b0ed
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52de5368f5ce61262c2d589ee36ea6650cbb194994badad3cc71c4ee2f14c31
+oid sha256:9a0d178020fecc5513a454227b25f3a8a60c61c1b470c9504f50321e953b23a6
 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": 0.0198000198000198,
+  "epoch": 0.0297000297000297,
   "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": 11.97,
       "eval_steps_per_second": 5.988,
       "step": 100
+    },
+    {
+      "epoch": 0.02178002178002178,
+      "grad_norm": 0.9592312574386597,
+      "learning_rate": 0.0002,
+      "loss": 3.1673,
+      "step": 110
+    },
+    {
+      "epoch": 0.02376002376002376,
+      "grad_norm": 1.070432186126709,
+      "learning_rate": 0.0002,
+      "loss": 3.1173,
+      "step": 120
+    },
+    {
+      "epoch": 0.02574002574002574,
+      "grad_norm": 2.247570753097534,
+      "learning_rate": 0.0002,
+      "loss": 3.7768,
+      "step": 130
+    },
+    {
+      "epoch": 0.02772002772002772,
+      "grad_norm": 1.5730074644088745,
+      "learning_rate": 0.0002,
+      "loss": 3.3516,
+      "step": 140
+    },
+    {
+      "epoch": 0.0297000297000297,
+      "grad_norm": 1.3724550008773804,
+      "learning_rate": 0.0002,
+      "loss": 3.2577,
+      "step": 150
+    },
+    {
+      "epoch": 0.0297000297000297,
+      "eval_loss": 0.8379923701286316,
+      "eval_runtime": 177.6782,
+      "eval_samples_per_second": 11.971,
+      "eval_steps_per_second": 5.988,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.883900991012864e+16,
+  "total_flos": 7.3218937061376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null