Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81cf41eaef9cdee65f59961e12e426e6df95539811f99b60862c313f8200e54e
+oid sha256:a54f9f423ae0a8098a29de3da3bd0e9c38bd4b551225bb78cc3b792f97b718a8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784c970c77e1c2242559b40d87790b23c8bd24cc7c34894b205b7292ef9f4664
+oid sha256:e540daaaa28f49d36eceaa194cd87cc0d2c5411861b6df9e9af623d86abed252
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3523a37ab88d78ad4cf956d02f94ea22563934c62f7c91745eb5c6303c1194
+oid sha256:8df5b0601170dedc7fb3816869722e4a1064c4d6d09140d08bf1f5e006e2abd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12981744421906694,
+  "epoch": 0.15145368492224476,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 8.953,
       "eval_steps_per_second": 4.476,
       "step": 54
+    },
+    {
+      "epoch": 0.13702952445345953,
+      "grad_norm": 1.0093810558319092,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 1.1367,
+      "step": 57
+    },
+    {
+      "epoch": 0.14424160468785216,
+      "grad_norm": 0.9035248160362244,
+      "learning_rate": 0.0001,
+      "loss": 1.2007,
+      "step": 60
+    },
+    {
+      "epoch": 0.15145368492224476,
+      "grad_norm": 1.1476191282272339,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 1.1702,
+      "step": 63
+    },
+    {
+      "epoch": 0.15145368492224476,
+      "eval_loss": 1.1219838857650757,
+      "eval_runtime": 156.5351,
+      "eval_samples_per_second": 8.956,
+      "eval_steps_per_second": 4.478,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.224630179481518e+17,
+  "total_flos": 3.761757705040036e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null