Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40b6a27ce45800aac91ae6a52e2c5d952bc98cc1743faf4bc03d21170e50d58
+oid sha256:af392bdd238c7dec56a878f8e7a9f703dbb092e68deb6d265e6f3e13c056d929
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c0d06ca17a9800ad29c0ec22d7d949f44f2c2a6bd2de7148eba1856cd04077
+oid sha256:e37860f528a0b494fd027d21f377b5256fc4b346b9b870685ca5ccdca75fbc06
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
+oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018018018018018018,
+  "epoch": 0.02702702702702703,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 13.251,
       "eval_steps_per_second": 13.251,
       "step": 6
+    },
+    {
+      "epoch": 0.021021021021021023,
+      "grad_norm": 5.296385765075684,
+      "learning_rate": 0.0001,
+      "loss": 2.1297,
+      "step": 7
+    },
+    {
+      "epoch": 0.024024024024024024,
+      "grad_norm": 3.105656623840332,
+      "learning_rate": 0.00012,
+      "loss": 2.0236,
+      "step": 8
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 3.085301399230957,
+      "learning_rate": 0.00014,
+      "loss": 1.7983,
+      "step": 9
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "eval_loss": 2.1258544921875,
+      "eval_runtime": 5.0108,
+      "eval_samples_per_second": 14.169,
+      "eval_steps_per_second": 14.169,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null