Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c932c6ae3585d6418bd30e2e2e20e5ed42e59ee50c51cee3d3f37cdcc67b9b
+oid sha256:0c8287c8869260c4c85989bd9948ddf035bea47bbfdd72f8cdc6de4f059342b3
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58f66156ff854172a9fbfd3958149fdb88b746b458bbf60b2da062db3a7b8f95
+oid sha256:9dd3c5a4c462a933b3af35eb8e16af5811bdf7f7bdac44f82208e58c03c6527c
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc3e1a62d8bdb6cd0fd5edd386e569d84463a4ef241f0f2e513f44529b47423
+oid sha256:5ff5f128f5dc83298480436fdf1f6f224dec3de6b70c5c8269cb668f3452b9ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf4f686b8bfa4a567357685a3d044a05c5668cbd2b7bc03da866263f614f62d
+oid sha256:176274aa8e238289b932fdb4b5ee216a9bcecc8dbc9ca7a6e0463ca9c6ff3c68
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3582770824432373,
-  "best_model_checkpoint": "results/checkpoint-7500",
-  "epoch": 0.7164008023688987,
+  "best_metric": 0.3561370372772217,
+  "best_model_checkpoint": "results/checkpoint-8500",
+  "epoch": 0.8119209093514185,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,36 @@
       "eval_samples_per_second": 239.137,
       "eval_steps_per_second": 3.74,
       "step": 7500
+    },
+    {
+      "epoch": 0.7641608558601586,
+      "grad_norm": 5.345180988311768,
+      "learning_rate": 3.089597860349604e-05,
+      "loss": 0.4032,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7641608558601586,
+      "eval_loss": 0.3689400851726532,
+      "eval_runtime": 110.4919,
+      "eval_samples_per_second": 236.678,
+      "eval_steps_per_second": 3.702,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8119209093514185,
+      "grad_norm": 3.314952850341797,
+      "learning_rate": 2.9701977266214542e-05,
+      "loss": 0.4101,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8119209093514185,
+      "eval_loss": 0.3561370372772217,
+      "eval_runtime": 112.2203,
+      "eval_samples_per_second": 233.033,
+      "eval_steps_per_second": 3.645,
+      "step": 8500
     }
   ],
   "logging_steps": 500,
@@ -251,7 +281,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2632052105216e+17,
+  "total_flos": 1.43163257192448e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null