Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5798fb376cb521b651dd28099ce2c086647fdcbbb595c40f31e09f0bca4fabf
+oid sha256:c4bab5d72981e47677ba7684e8cd3fae37040400aa8bac37bf81762e339478b9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47df0430f355abf76b457d4820080696300cbebbc336555910b86ea1f907aefe
+oid sha256:2e995c2d7fcce2a965e868612f149f264b8568bb4ae703c7a74f350a4edd815b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70bd3f5a04474750befb510a828eb2569e420cfa0abc940751ff6ccd74605249
+oid sha256:216f08fcc7c6d0fb430357ce223cfcb24bd8f8402de822cacacf80e67d804372
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bbb5cc30267ffbb6fcba5b12ec3b2b908df1e2e422c7d381d682f082ea4159
+oid sha256:507bfe4270aab5b2aa070e93d9c3404af996914dd61586771e0cc504e5b0252c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13224074597343882,
+  "epoch": 0.1469341621927098,
   "eval_steps": 13,
-  "global_step": 117,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,42 @@
       "eval_samples_per_second": 6.622,
       "eval_steps_per_second": 0.831,
       "step": 117
+    },
+    {
+      "epoch": 0.13563153433173214,
+      "grad_norm": 1.7210478782653809,
+      "learning_rate": 5.454212938299255e-06,
+      "loss": 0.5592,
+      "step": 120
+    },
+    {
+      "epoch": 0.13902232269002543,
+      "grad_norm": 1.005109429359436,
+      "learning_rate": 4.4499481138022544e-06,
+      "loss": 0.4997,
+      "step": 123
+    },
+    {
+      "epoch": 0.14241311104831875,
+      "grad_norm": 1.0120928287506104,
+      "learning_rate": 3.5387801599533475e-06,
+      "loss": 0.543,
+      "step": 126
+    },
+    {
+      "epoch": 0.14580389940661204,
+      "grad_norm": 0.9547510743141174,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.5363,
+      "step": 129
+    },
+    {
+      "epoch": 0.1469341621927098,
+      "eval_loss": 0.12771442532539368,
+      "eval_runtime": 224.7527,
+      "eval_samples_per_second": 6.63,
+      "eval_steps_per_second": 0.832,
+      "step": 130
     }
   ],
   "logging_steps": 3,
@@ -379,7 +415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.290649822662492e+17,
+  "total_flos": 3.6562775807361024e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null