Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a1d115a5ed8dca79f0286bff6d97ce9f3619349eddbe1e234f665c5d710ff7d
+oid sha256:26cdab1b0d375bdd23565aa0077f6a65dd30f31149be06116d841a3b8feb3920
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96791c50a99e9e2d5541f0414589a9e4889fae96b0249c57dfb43ab56e2f4e6a
+oid sha256:fad6f35856a1fb7fd23e18813fe2cb9c2216d4becd30b398a6c8d6e014b1b331
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d0fb11851d2e6866412be474386ca9783388985f6b485365d6777e2b3d791f
+oid sha256:e36897f9547b352e823f9278793dec524937b492282033ac58955b130dceb9f8
 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": 0.0022571834864456132,
+  "epoch": 0.00338577522966842,
   "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": 30.978,
       "eval_steps_per_second": 15.491,
       "step": 100
+    },
+    {
+      "epoch": 0.0024829018350901746,
+      "grad_norm": 0.985332190990448,
+      "learning_rate": 0.0002,
+      "loss": 2.1047,
+      "step": 110
+    },
+    {
+      "epoch": 0.002708620183734736,
+      "grad_norm": 0.9166615605354309,
+      "learning_rate": 0.0002,
+      "loss": 2.0444,
+      "step": 120
+    },
+    {
+      "epoch": 0.002934338532379297,
+      "grad_norm": 1.0133342742919922,
+      "learning_rate": 0.0002,
+      "loss": 2.1059,
+      "step": 130
+    },
+    {
+      "epoch": 0.0031600568810238585,
+      "grad_norm": 0.786649227142334,
+      "learning_rate": 0.0002,
+      "loss": 2.1281,
+      "step": 140
+    },
+    {
+      "epoch": 0.00338577522966842,
+      "grad_norm": 1.0310282707214355,
+      "learning_rate": 0.0002,
+      "loss": 2.2372,
+      "step": 150
+    },
+    {
+      "epoch": 0.00338577522966842,
+      "eval_loss": 2.126699686050415,
+      "eval_runtime": 300.9393,
+      "eval_samples_per_second": 30.993,
+      "eval_steps_per_second": 15.498,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9060952162959360.0,
+  "total_flos": 1.3508300242944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null