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:bcf47242fdb2d4bc4a70fb246887cdf47886b84caad800955c05be8efce1cb4d
+oid sha256:cd210b2e3be1deefd43b07039178256a298c6c8efba7af2e85d19c1562ec261a
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e098710ae320637de83726ef9158521fca79d9ac7438aeda0d1ea94b9ad9fbb9
+oid sha256:493421d517a68d4222219039e94f1c6e4f5aae546bcafed8f4c7d5c0a30f2cba
 size 113528596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a9bfec275e3717cc57c1021fdb7bae65637cf0dc882fb7ab3d6099862b5f5f1
+oid sha256:bf95dc75f3738cdab19607c88ff1a52c0fd432992f39b094cf2968f0205e89b3
 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": 0.00938174312787316,
+  "epoch": 0.014072614691809739,
   "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": 9.155,
       "eval_steps_per_second": 4.577,
       "step": 100
+    },
+    {
+      "epoch": 0.010319917440660475,
+      "grad_norm": 0.5788394808769226,
+      "learning_rate": 0.0002,
+      "loss": 1.0154,
+      "step": 110
+    },
+    {
+      "epoch": 0.01125809175344779,
+      "grad_norm": 0.5604102611541748,
+      "learning_rate": 0.0002,
+      "loss": 1.1134,
+      "step": 120
+    },
+    {
+      "epoch": 0.012196266066235107,
+      "grad_norm": 0.836513876914978,
+      "learning_rate": 0.0002,
+      "loss": 1.1753,
+      "step": 130
+    },
+    {
+      "epoch": 0.013134440379022422,
+      "grad_norm": 1.2483829259872437,
+      "learning_rate": 0.0002,
+      "loss": 1.0936,
+      "step": 140
+    },
+    {
+      "epoch": 0.014072614691809739,
+      "grad_norm": 0.7146385312080383,
+      "learning_rate": 0.0002,
+      "loss": 1.0279,
+      "step": 150
+    },
+    {
+      "epoch": 0.014072614691809739,
+      "eval_loss": 0.5074164867401123,
+      "eval_runtime": 245.1114,
+      "eval_samples_per_second": 9.155,
+      "eval_steps_per_second": 4.578,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1999597215744e+16,
+  "total_flos": 4.8595133005824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null