Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8838cfd1ed0bc19e91b5a81645cbfeae2b22006d9ec0630929198bed13057925
+oid sha256:5ac01be4e4efadb46ae0a5aee8b3d4bd8d42c622a224365887fe78ebf53b5ab5
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1694a21b60db646930f981906f7617666debe86f16c9096862c34b8c05b1dd
+oid sha256:eb274ef53fb2cd8d846c51a7ef4341bac838a69fab940cb45f7574bf00490432
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa173be0daf3b70291aa54f3fc172b70d25960de7e9a07e7f57c5f27ae513c9
+oid sha256:28cb1b5e093b2599d8fa1806646d1f09bc9ce7ac92f9796c6863470342508537
 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": 0.0009177974696323762,
+  "epoch": 0.0013766962044485644,
   "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": 63.755,
       "eval_steps_per_second": 31.878,
       "step": 100
+    },
+    {
+      "epoch": 0.0010095772165956138,
+      "grad_norm": 5.495555877685547,
+      "learning_rate": 0.0002,
+      "loss": 2.8344,
+      "step": 110
+    },
+    {
+      "epoch": 0.0011013569635588514,
+      "grad_norm": 4.5758376121521,
+      "learning_rate": 0.0002,
+      "loss": 3.0487,
+      "step": 120
+    },
+    {
+      "epoch": 0.001193136710522089,
+      "grad_norm": 5.466923713684082,
+      "learning_rate": 0.0002,
+      "loss": 2.888,
+      "step": 130
+    },
+    {
+      "epoch": 0.0012849164574853266,
+      "grad_norm": 3.5546038150787354,
+      "learning_rate": 0.0002,
+      "loss": 2.8088,
+      "step": 140
+    },
+    {
+      "epoch": 0.0013766962044485644,
+      "grad_norm": 4.920299053192139,
+      "learning_rate": 0.0002,
+      "loss": 2.7983,
+      "step": 150
+    },
+    {
+      "epoch": 0.0013766962044485644,
+      "eval_loss": 2.8186566829681396,
+      "eval_runtime": 721.1975,
+      "eval_samples_per_second": 63.612,
+      "eval_steps_per_second": 31.807,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4894777933824000.0,
+  "total_flos": 7342166900736000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null