Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3139596ba86de86f46a91e4d6d4b9795aba6ec437c5a3a5f02a69374e94832e2
+oid sha256:69c451bb6a82f6c3d42d469140c1048f2170d3008e6c1c9bd066561cec948d3e
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7cabb00d4032a3eaa6ce9b12f7d87615f18d1a41326b33f822bd7a852c1cff8
+oid sha256:411b78174724e914e18c816c5d45bf1904d221a4533c3af32065cece8c2c8ee3
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5fe19afda7a8f7505ad1e5e6a50f7fa50dd4ca294e417d083e61d478b04cf0
+oid sha256:3a3a6084dcf7cadde36acaef2f1d8a6bf36dcb050a9d45415d7af39f8ebdd718
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d99dc7a150ff6ed818c8735e9e9061e757b4b841b8d74bde2c9d7a2195ff136
+oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11560256894597658,
+  "epoch": 0.12844729882886285,
   "eval_steps": 17,
-  "global_step": 153,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -444,6 +444,49 @@
       "eval_samples_per_second": 36.077,
       "eval_steps_per_second": 4.514,
       "step": 153
+    },
+    {
+      "epoch": 0.11786928598413299,
+      "grad_norm": 0.05935904011130333,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 12.4428,
+      "step": 156
+    },
+    {
+      "epoch": 0.12013600302228938,
+      "grad_norm": 0.06513120234012604,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 12.4436,
+      "step": 159
+    },
+    {
+      "epoch": 0.1224027200604458,
+      "grad_norm": 0.060658689588308334,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 12.4426,
+      "step": 162
+    },
+    {
+      "epoch": 0.12466943709860219,
+      "grad_norm": 0.06469012796878815,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 12.4421,
+      "step": 165
+    },
+    {
+      "epoch": 0.1269361541367586,
+      "grad_norm": 0.05972781777381897,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 12.4421,
+      "step": 168
+    },
+    {
+      "epoch": 0.12844729882886285,
+      "eval_loss": 12.442495346069336,
+      "eval_runtime": 61.8344,
+      "eval_samples_per_second": 36.064,
+      "eval_steps_per_second": 4.512,
+      "step": 170
     }
   ],
   "logging_steps": 3,
@@ -463,7 +506,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 338801197056.0,
+  "total_flos": 376719802368.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null