Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62532d5f8e21eb02dc93bec707dc21d939ae8d4751f4be929d9a7303a2dbfa3c
+oid sha256:d03982413859bedc94fe47ed37ef219abc203977342732b3243820543d698cce
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7afdaa4aa3fd94db2282fab43e0da35f8dcc2e7065253cbea7e606c7806065a
+oid sha256:2b8a698809f6fddee282584af607f3f77c59b4a88f9884d0963b5c016c901d10
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e3e3253b1e11d5b911b90c9d12eee8f8449ea7e8df10ad506caaaaa9049447
+oid sha256:9e02e7bd90ca98ed6791b0f054fa59a251abaaa202b575115cd160182e14bfeb
 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": 0.061381074168797956,
+  "epoch": 0.07161125319693094,
   "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": 155.537,
       "eval_steps_per_second": 39.042,
       "step": 54
+    },
+    {
+      "epoch": 0.06479113384484228,
+      "grad_norm": 1.2141445875167847,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 43.8766,
+      "step": 57
+    },
+    {
+      "epoch": 0.06820119352088662,
+      "grad_norm": 1.179465413093567,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 43.7685,
+      "step": 60
+    },
+    {
+      "epoch": 0.07161125319693094,
+      "grad_norm": 0.8835251331329346,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 43.8831,
+      "step": 63
+    },
+    {
+      "epoch": 0.07161125319693094,
+      "eval_loss": 10.942551612854004,
+      "eval_runtime": 4.747,
+      "eval_samples_per_second": 156.099,
+      "eval_steps_per_second": 39.183,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 481917665280.0,
+  "total_flos": 566718627840.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null