Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d03982413859bedc94fe47ed37ef219abc203977342732b3243820543d698cce
+oid sha256:dcde46922143049b9245734529a5e64c31f2f7305532314b1ac55ed3baa635cc
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8a698809f6fddee282584af607f3f77c59b4a88f9884d0963b5c016c901d10
+oid sha256:6639522835626391eb5b4f47e0a41c4cb163b7913c17c522755321d98cbcfc80
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e02e7bd90ca98ed6791b0f054fa59a251abaaa202b575115cd160182e14bfeb
+oid sha256:12002707d6533b4858bef1387878cda57708ad78dd95cf4b6295e0d81c054e61
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07161125319693094,
+  "epoch": 0.08184143222506395,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 156.099,
       "eval_steps_per_second": 39.183,
       "step": 63
+    },
+    {
+      "epoch": 0.07502131287297528,
+      "grad_norm": 1.0751994848251343,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 43.777,
+      "step": 66
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 1.384466528892517,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 43.6297,
+      "step": 69
+    },
+    {
+      "epoch": 0.08184143222506395,
+      "grad_norm": 1.247775912284851,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 43.7553,
+      "step": 72
+    },
+    {
+      "epoch": 0.08184143222506395,
+      "eval_loss": 10.936705589294434,
+      "eval_runtime": 4.7575,
+      "eval_samples_per_second": 155.753,
+      "eval_steps_per_second": 39.096,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 566718627840.0,
+  "total_flos": 643246325760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null