Training in progress, step 63000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fd7d3229c28617cd8b7ee9c5b265a0b6c8e5c1472537520b44ebd5131a34fe
+oid sha256:73903da31c9b9d848fa3dc081b0cc0b8784e6aef4a1ec1bce8df8211ea090227
 size 1882177840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d94f47d1cd577af82550ce480e1d26bff5ac1076a79522e98f2d5f6d846e3c5
+oid sha256:b7f41f1d65446549e90258f21fed00d90b0c96c4f8a66571ccae685e2c8b63d5
 size 37161530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3814db4cbaa1d1f7ae10f72fc8ff620b9669469050d4879f09f386790fbc59
+oid sha256:9c29d4681b39690eaaafbf2164900dcbb7e4adbbf215e4232929b945620d1964
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9233d091885437459c3c43d3eb157cdd78c220a64977478d6fbab6ba06baa1a
+oid sha256:3bbd1aa5de53f2295365b6cba9c613b814db5492cf7e5c0c7f70f0bb0df8980c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6949540774345632,
+  "epoch": 0.7005137100540396,
   "eval_steps": 1000,
-  "global_step": 62500,
+  "global_step": 63000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4897,6 +4897,49 @@
       "learning_rate": 4.259859885713584e-05,
       "loss": 1.9038,
       "step": 62500
+    },
+    {
+      "epoch": 0.6960660039584584,
+      "grad_norm": 0.0,
+      "learning_rate": 4.231259127717636e-05,
+      "loss": 1.9314,
+      "step": 62600
+    },
+    {
+      "epoch": 0.6971779304823538,
+      "grad_norm": 0.0,
+      "learning_rate": 4.2027289200206564e-05,
+      "loss": 1.8182,
+      "step": 62700
+    },
+    {
+      "epoch": 0.698289857006249,
+      "grad_norm": 0.0,
+      "learning_rate": 4.174269611540145e-05,
+      "loss": 1.7234,
+      "step": 62800
+    },
+    {
+      "epoch": 0.6994017835301444,
+      "grad_norm": 0.0,
+      "learning_rate": 4.1458815503265315e-05,
+      "loss": 1.9986,
+      "step": 62900
+    },
+    {
+      "epoch": 0.7005137100540396,
+      "grad_norm": 0.0,
+      "learning_rate": 4.117565083558909e-05,
+      "loss": 1.9098,
+      "step": 63000
+    },
+    {
+      "epoch": 0.7005137100540396,
+      "eval_loss": 2.144634485244751,
+      "eval_runtime": 29.3973,
+      "eval_samples_per_second": 2.041,
+      "eval_steps_per_second": 2.041,
+      "step": 63000
     }
   ],
   "logging_steps": 100,
@@ -4916,7 +4959,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1770566229056e+17,
+  "total_flos": 1.181810744019456e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null