Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e38be8cd3e1789ae3735b27b93488654df375a71639ec1f526d2c27acecfe1
+oid sha256:8d099b8068a756a5c9e29a9d88203e169057bb4b52f16660f6edb1b7eaab3abb
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6458122ec561144054fbf12a86dc7bb4c1b34b06bc5aec29eed362d2529c40b9
+oid sha256:e85afd394eef4b45bc218e7af5de4e28dd79a59a5250a8e95fa58dc2194a6695
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09f9d8c9e048830f98d8554060bfff7f6550357d501c02f1cbd2ff879b1e61e
+oid sha256:16b7b2ce25b347a7a970441d627b3f3a7a67e557c32db36074bd43a52b496dfa
 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": 0.007029259291802126,
+  "epoch": 0.010543888937703189,
   "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": 16.688,
       "eval_steps_per_second": 8.344,
       "step": 100
+    },
+    {
+      "epoch": 0.007732185220982339,
+      "grad_norm": 18.93454360961914,
+      "learning_rate": 0.0002,
+      "loss": 4.3874,
+      "step": 110
+    },
+    {
+      "epoch": 0.008435111150162551,
+      "grad_norm": 17.588722229003906,
+      "learning_rate": 0.0002,
+      "loss": 3.9864,
+      "step": 120
+    },
+    {
+      "epoch": 0.009138037079342765,
+      "grad_norm": 20.59840202331543,
+      "learning_rate": 0.0002,
+      "loss": 4.4036,
+      "step": 130
+    },
+    {
+      "epoch": 0.009840963008522977,
+      "grad_norm": 18.34351348876953,
+      "learning_rate": 0.0002,
+      "loss": 4.7032,
+      "step": 140
+    },
+    {
+      "epoch": 0.010543888937703189,
+      "grad_norm": 24.309648513793945,
+      "learning_rate": 0.0002,
+      "loss": 4.3665,
+      "step": 150
+    },
+    {
+      "epoch": 0.010543888937703189,
+      "eval_loss": 1.0576177835464478,
+      "eval_runtime": 359.2103,
+      "eval_samples_per_second": 16.675,
+      "eval_steps_per_second": 8.338,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0715537998741504e+16,
+  "total_flos": 4.635811583832883e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null