Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad0d6da1cb2aff0abea77e81d3e33ce4fc494829579fa0893901eb7cc31e441
+oid sha256:0137c42305e3b5b42b68380e118e2fea520c219c17291e6a56a6ab96c8cad0de
 size 6614970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009307033208657868,
+  "epoch": 0.0013960549812986802,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 154.978,
       "eval_steps_per_second": 77.493,
       "step": 10
+    },
+    {
+      "epoch": 0.0010237736529523655,
+      "grad_norm": Infinity,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 115.25,
+      "step": 11
+    },
+    {
+      "epoch": 0.001116843985038944,
+      "grad_norm": Infinity,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 103.25,
+      "step": 12
+    },
+    {
+      "epoch": 0.0012099143171255228,
+      "grad_norm": Infinity,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 111.4375,
+      "step": 13
+    },
+    {
+      "epoch": 0.0013029846492121015,
+      "grad_norm": Infinity,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 115.5,
+      "step": 14
+    },
+    {
+      "epoch": 0.0013960549812986802,
+      "grad_norm": Infinity,
+      "learning_rate": 5e-05,
+      "loss": 111.2812,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013960549812986802,
+      "eval_loss": 7.2212815284729,
+      "eval_runtime": 115.3728,
+      "eval_samples_per_second": 156.857,
+      "eval_steps_per_second": 78.433,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 300278611968000.0,
+  "total_flos": 450417917952000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null