Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0304712f1eb1a3bab6a66891b135d7db9a472b1364fa7a020cc0590a373691d5
+oid sha256:2019092eaab1c98d8ffa6cf5daa900efe89c20c779c04a0660fe242aa83dc4a2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aaff82afdcc3a7190016ddf1d0f98ebf329fa246ef8ea7afca29534245e1b41
+oid sha256:0825add271cb1928713806d119b0318708f8a4bddc391a2ecb983e76aec8a81c
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6537e434778211ceaf8a863d4d8984f5efaf5b467b798fc7ec30bbe158933e
+oid sha256:22ccfd88f620eb832cdc95b7c73f631ee104fb7843f178a425bf2208b904d28d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02952029520295203,
+  "epoch": 0.03444034440344403,
   "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": 7.289,
       "eval_steps_per_second": 0.913,
       "step": 54
+    },
+    {
+      "epoch": 0.031160311603116032,
+      "grad_norm": 0.20679989457130432,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.5339,
+      "step": 57
+    },
+    {
+      "epoch": 0.03280032800328003,
+      "grad_norm": 0.16482852399349213,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.5692,
+      "step": 60
+    },
+    {
+      "epoch": 0.03444034440344403,
+      "grad_norm": 0.1565546691417694,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.5936,
+      "step": 63
+    },
+    {
+      "epoch": 0.03444034440344403,
+      "eval_loss": 0.606318473815918,
+      "eval_runtime": 422.8445,
+      "eval_samples_per_second": 7.286,
+      "eval_steps_per_second": 0.913,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.421352351301632e+17,
+  "total_flos": 1.6527352922112e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null