Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1d7127332ea896fc1c64810b1d01093190d6a464f3959bb11c14d71a512d575
+oid sha256:3e41f3d6ccf0b8002faa93d45351d1e713bcb0dfaba156f735cab35d3ec809f1
 size 124606

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b552b23950e04203fc6b6ebf40153815af5970ba452935e86f3e6e747596161b
+oid sha256:5f1fc61747dcb58231472ea223e91876f35971050b45a3dce9ab391a74c5e432
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0eff3cb96e86afa6459edc23315fcd4b4398aa38aa5e6b311873974c5b5b02
+oid sha256:2f31b7376f2a92936dba507b5525d9a8f221ad69bde7794ecc4198c92780b28c
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006421061080343527,
+  "epoch": 0.012842122160687053,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 310.385,
       "eval_steps_per_second": 77.626,
       "step": 5
+    },
+    {
+      "epoch": 0.007705273296412232,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.008989485512480938,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.010273697728549643,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.011557909944618349,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.012842122160687053,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.012842122160687053,
+      "eval_loss": NaN,
+      "eval_runtime": 16.9593,
+      "eval_samples_per_second": 309.329,
+      "eval_steps_per_second": 77.362,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 17627190657024.0,
+  "total_flos": 34993624055808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null