Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c109aa6c05e83e81fd9fae11bfa61cc2d9528196064f893d40862948038533
+oid sha256:8838cfd1ed0bc19e91b5a81645cbfeae2b22006d9ec0630929198bed13057925
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc23ad10e8ff024f2e5dd7a2166f8dbc531521be6e85a458e5eae0be327f8d21
+oid sha256:ef1694a21b60db646930f981906f7617666debe86f16c9096862c34b8c05b1dd
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0327c646fbcebdbfe58bb39ffa0aa64a521ffb921c8df37b9e57436d246f1866
+oid sha256:caa173be0daf3b70291aa54f3fc172b70d25960de7e9a07e7f57c5f27ae513c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004588987348161881,
+  "epoch": 0.0009177974696323762,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 63.628,
       "eval_steps_per_second": 31.815,
       "step": 50
+    },
+    {
+      "epoch": 0.0005506784817794257,
+      "grad_norm": 6.173509120941162,
+      "learning_rate": 0.0002,
+      "loss": 3.0467,
+      "step": 60
+    },
+    {
+      "epoch": 0.0006424582287426633,
+      "grad_norm": 2.9664249420166016,
+      "learning_rate": 0.0002,
+      "loss": 3.0159,
+      "step": 70
+    },
+    {
+      "epoch": 0.0007342379757059009,
+      "grad_norm": 3.5428833961486816,
+      "learning_rate": 0.0002,
+      "loss": 3.0559,
+      "step": 80
+    },
+    {
+      "epoch": 0.0008260177226691386,
+      "grad_norm": 4.495511054992676,
+      "learning_rate": 0.0002,
+      "loss": 2.8184,
+      "step": 90
+    },
+    {
+      "epoch": 0.0009177974696323762,
+      "grad_norm": 4.205393314361572,
+      "learning_rate": 0.0002,
+      "loss": 2.8674,
+      "step": 100
+    },
+    {
+      "epoch": 0.0009177974696323762,
+      "eval_loss": 2.848527431488037,
+      "eval_runtime": 719.5853,
+      "eval_samples_per_second": 63.755,
+      "eval_steps_per_second": 31.878,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2447388966912000.0,
+  "total_flos": 4894777933824000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null