Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c96a98c8e8c0ebe728488647f7b680178769e3ea0b0f466c9b9934406668b5c
+oid sha256:773fa93fe76ab7791629b47f41ded64ca562e499258b5e51bef7f87bbd1862d4
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c2e89a0dfa486bc5dd5d13c6241da684f7f7653be35deaa6bc5f1d060ea20b
+oid sha256:571bb9bd682830424c8b3d51e3c5b5c7060d9da83a72eec0ee61f1b8e66b2801
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c1e33264acca2abb6dd72706d07111d0f013ace21da22da195123054b2c451
+oid sha256:efd8cea30ce7a2b77d26a2e7c8d59aa8e60e47700db2c54a576edce7ea1b2144
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4172517552657974,
+  "epoch": 0.6258776328986961,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 9.363,
       "eval_steps_per_second": 4.682,
       "step": 26
+    },
+    {
+      "epoch": 0.43329989969909727,
+      "grad_norm": 0.12099477648735046,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.4904,
+      "step": 27
+    },
+    {
+      "epoch": 0.4493480441323972,
+      "grad_norm": 0.13227578997612,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.5992,
+      "step": 28
+    },
+    {
+      "epoch": 0.4653961885656971,
+      "grad_norm": 0.11921201646327972,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.4221,
+      "step": 29
+    },
+    {
+      "epoch": 0.48144433299899697,
+      "grad_norm": 0.12202885746955872,
+      "learning_rate": 5e-05,
+      "loss": 2.624,
+      "step": 30
+    },
+    {
+      "epoch": 0.4974924774322969,
+      "grad_norm": 0.11582452803850174,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.4619,
+      "step": 31
+    },
+    {
+      "epoch": 0.5135406218655968,
+      "grad_norm": 0.11963976919651031,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.4558,
+      "step": 32
+    },
+    {
+      "epoch": 0.5295887662988967,
+      "grad_norm": 0.13530096411705017,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.3744,
+      "step": 33
+    },
+    {
+      "epoch": 0.5456369107321966,
+      "grad_norm": 0.1295008808374405,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.3498,
+      "step": 34
+    },
+    {
+      "epoch": 0.5616850551654965,
+      "grad_norm": 0.11402874439954758,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.514,
+      "step": 35
+    },
+    {
+      "epoch": 0.5777331995987964,
+      "grad_norm": 0.12555132806301117,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.3917,
+      "step": 36
+    },
+    {
+      "epoch": 0.5937813440320963,
+      "grad_norm": 0.11757726967334747,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.5616,
+      "step": 37
+    },
+    {
+      "epoch": 0.6098294884653962,
+      "grad_norm": 0.12606336176395416,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.5237,
+      "step": 38
+    },
+    {
+      "epoch": 0.6258776328986961,
+      "grad_norm": 0.12942460179328918,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.4834,
+      "step": 39
+    },
+    {
+      "epoch": 0.6258776328986961,
+      "eval_loss": 2.511258840560913,
+      "eval_runtime": 22.4533,
+      "eval_samples_per_second": 9.353,
+      "eval_steps_per_second": 4.676,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2999268126162944e+16,
+  "total_flos": 1.949113679609856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null