Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51938a86b21da17a4ccef7bae1068387c4ca94c38d4d5c37ed121979b35931c8
+oid sha256:67bfbd23435c3471571334f845a66cd5681aa7bdd7e70fba99b2401d95003630
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e4fe83f24b7f7661dd68902f384101f822537fcce9754332361e66da67f6d17
+oid sha256:fb6859cacdb6a9367cb13b21861953eb09a6a541a4f1065af7e0e7a1af13a730
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0498481dc13586eb056bf15062506f1ff8e314200eb2c09558f026d1062ec3a
+oid sha256:db7d6da1e0e5f17020a86468fe3671b773406443e6a903eda7622cee05ea7fe6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
+oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0063071033751762925,
+  "epoch": 0.007568524050211551,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 8.836,
       "eval_steps_per_second": 4.418,
       "step": 45
+    },
+    {
+      "epoch": 0.006727576933521378,
+      "grad_norm": 0.9200890064239502,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 1.3726,
+      "step": 48
+    },
+    {
+      "epoch": 0.007148050491866465,
+      "grad_norm": 0.962693989276886,
+      "learning_rate": 0.0001346117057077493,
+      "loss": 1.3319,
+      "step": 51
+    },
+    {
+      "epoch": 0.007568524050211551,
+      "grad_norm": 0.935663640499115,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 1.3547,
+      "step": 54
+    },
+    {
+      "epoch": 0.007568524050211551,
+      "eval_loss": 1.3415731191635132,
+      "eval_runtime": 2673.8225,
+      "eval_samples_per_second": 8.989,
+      "eval_steps_per_second": 4.494,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6856376277925888e+17,
+  "total_flos": 3.2227651533511066e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null