Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a43a5c36d3cd82d0af0c034630bb72b16d9819edd251e67192455246d9b24f
+oid sha256:495ee1ed71e7349cdbfeb34358d8c4765d6e8a4d29744d7baa56f5c626a1fce6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a444169326383cad05232d99df8cf8a75cdc190da79eaaa36a6fbed832afc850
+oid sha256:f0470e2308f8321fc41c5df5aede03ac6f5c7087adf88392b8b1c0fed044208c
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0385d0910727328e26f9e184ee6b02fb5faca32bbe5b4b34fd72a216de0763
+oid sha256:1e8641384676c0c3ca843dcc47e3f6d9bd5a859182c78c26888d7b28bf27a1bf
 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": 0.004920049200492005,
+  "epoch": 0.00984009840098401,
   "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": 7.286,
       "eval_steps_per_second": 0.913,
       "step": 9
+    },
+    {
+      "epoch": 0.006560065600656006,
+      "grad_norm": 0.3018288016319275,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.8476,
+      "step": 12
+    },
+    {
+      "epoch": 0.008200082000820008,
+      "grad_norm": 0.2912035286426544,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.6816,
+      "step": 15
+    },
+    {
+      "epoch": 0.00984009840098401,
+      "grad_norm": 0.39786526560783386,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.7029,
+      "step": 18
+    },
+    {
+      "epoch": 0.00984009840098401,
+      "eval_loss": 0.6832850575447083,
+      "eval_runtime": 422.898,
+      "eval_samples_per_second": 7.285,
+      "eval_steps_per_second": 0.913,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.346884114939904e+16,
+  "total_flos": 4.693768229879808e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null