Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9963a9d86ae5a27f6ee066db8c5b562226104daceffd3c1575c7d4741f99efb2
+oid sha256:4c29db6726183c392e24e3f7ac73beacbf6281e32ca0b5759cdba57394d95509
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3953f19e246332a3675c1174a2c95872e3b1063c743cdcb2845c4535a8a1d1
+oid sha256:30ef3f07639a90449bac0570520825cb011e60dbefc6895deac8bab5d1461d3c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cff2c747df5d27ab1c0cefb01537565116302dd84350f85dd1a280d3f7af4e
+oid sha256:53f240075f9c021172880a964708e56b8df7bd9c9f7cf116a389f7bc4bc0f8fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004046307744183433,
+  "epoch": 0.008092615488366865,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 10.137,
       "eval_steps_per_second": 1.269,
       "step": 9
+    },
+    {
+      "epoch": 0.005395076992244577,
+      "grad_norm": 6.886386871337891,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 8.2046,
+      "step": 12
+    },
+    {
+      "epoch": 0.006743846240305721,
+      "grad_norm": 4.885524272918701,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 8.0238,
+      "step": 15
+    },
+    {
+      "epoch": 0.008092615488366865,
+      "grad_norm": 5.15069580078125,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 7.5582,
+      "step": 18
+    },
+    {
+      "epoch": 0.008092615488366865,
+      "eval_loss": 1.8677637577056885,
+      "eval_runtime": 369.696,
+      "eval_samples_per_second": 10.135,
+      "eval_steps_per_second": 1.269,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.003920218803405e+16,
+  "total_flos": 3.832057962273178e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null