Training in progress, step 165, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5150c2196969043314f566861c4849a7f9365e1cc6a686a4cdb2edb6fa4eddb5
+oid sha256:b1f826ff0deb5ca760bab1688322cba096707f0f6506ea0db49e64851b1b6e1b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1a35499a98ce19e19615db2fbac7d72d4a494f93b1298df13d80ee2cf6aec3
+oid sha256:304ef3fb9b06f4e634b17acfe8df2622465f353a24e78010c8336da55dc22a2d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d72c4d52a605fc99c729c21c0deb735993f9bc8ecba075dedb1f93e3a6ad9c7
+oid sha256:6728ffdf9bf59bf13703e6ecc746855ce34369dd62dc3ca69a894e5a32ceaccd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda70a7e2255bb2a6bed4064da315669732f8ee1496404c42573741f484eb69b
+oid sha256:b9d255475980828d00dffcac4a69741da74c7e5ef4f645ab21d69e57306e3317
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07824439146647105,
+  "epoch": 0.08068952869979827,
   "eval_steps": 34,
-  "global_step": 160,
+  "global_step": 165,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1167,6 +1167,41 @@
       "learning_rate": 2.6099108277934103e-05,
       "loss": 0.9811,
       "step": 160
+    },
+    {
+      "epoch": 0.0787334189131365,
+      "grad_norm": 0.36206722259521484,
+      "learning_rate": 2.4866811044312665e-05,
+      "loss": 1.1474,
+      "step": 161
+    },
+    {
+      "epoch": 0.07922244635980194,
+      "grad_norm": 0.38807740807533264,
+      "learning_rate": 2.36601717258897e-05,
+      "loss": 0.9162,
+      "step": 162
+    },
+    {
+      "epoch": 0.07971147380646738,
+      "grad_norm": 0.36179038882255554,
+      "learning_rate": 2.2479602388887012e-05,
+      "loss": 0.8902,
+      "step": 163
+    },
+    {
+      "epoch": 0.08020050125313283,
+      "grad_norm": 0.40321770310401917,
+      "learning_rate": 2.132550619665168e-05,
+      "loss": 0.8454,
+      "step": 164
+    },
+    {
+      "epoch": 0.08068952869979827,
+      "grad_norm": 0.3098496198654175,
+      "learning_rate": 2.0198277271976052e-05,
+      "loss": 1.0062,
+      "step": 165
     }
   ],
   "logging_steps": 1,
@@ -1186,7 +1221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.102326712880333e+17,
+  "total_flos": 7.324274422657843e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null