Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e41f3d6ccf0b8002faa93d45351d1e713bcb0dfaba156f735cab35d3ec809f1
+oid sha256:6c8559a8d0a2ea38925aa316251725b81d8f90cd9c228f7f24576f5cfe7acefe
 size 124606

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1fc61747dcb58231472ea223e91876f35971050b45a3dce9ab391a74c5e432
+oid sha256:9d4c88bcfb579b2e7508a39d1e3ecea98ce0d55cab783c43b0c3f30d514399d9
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f31b7376f2a92936dba507b5525d9a8f221ad69bde7794ecc4198c92780b28c
+oid sha256:b58ef7d8df65e566f7438a152a34c8bb3b894353cc82b46f586c77ce2cc450ea
 size 14512

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": 0.012842122160687053,
+  "epoch": 0.01926318324103058,
   "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": 309.329,
       "eval_steps_per_second": 77.362,
       "step": 10
+    },
+    {
+      "epoch": 0.01412633437675576,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.015410546592824464,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.016694758808893168,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.017978971024961876,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.01926318324103058,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.01926318324103058,
+      "eval_loss": NaN,
+      "eval_runtime": 16.9256,
+      "eval_samples_per_second": 309.945,
+      "eval_steps_per_second": 77.516,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 34993624055808.0,
+  "total_flos": 52620814712832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null