Training in progress, step 9, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9b0aecdcbc1ef6a985202ad21c9afbb7a09e1136b808cb6d87b5484ee23420
+oid sha256:0d071183cf96439c350e34aa15e2891d92ae15751eb7a90bab3cb51f88742af8
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb84b305596fb3cc68795959f612d65e961ddfa0d366482534e89f8bd43f72d
+oid sha256:09799671da1ea69e27816260f255ab65118b362db892ecca04e7dafa2c982395
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b1f4135482f8e6ab4c0bff25845dd231f3f6afd4b40b094907ed59535b63ae
+oid sha256:3c2ce919d02ca2e7faac6248be7322a4506ca8a6ce1c6e92c7b588c04c47e58d
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace520f7f3a46e3992e2ff8814c09d5ebddf402f03204522349e0d7986ebeca1
+oid sha256:3e71d5f72d49ed5fbb050112699254750b838c25c1714276c860434c918185ff
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8967b93bee541d58b2b16421a6b30a92c947d8c673b2f45392097ce8f3475830
+oid sha256:50339a44f3d749d22adbba653498ee59f154ec2bd1ff62cb1d67900c754843e7
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafd580388905e923d76cd19c2e149d4fa189b205109f9f6c9d69ad4bc0d4323
+oid sha256:cb7faef626932c51401cd184eb06e1b9c59b4ff7eb44bead02e81595a427aabb
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e943462f993b4c6778bc1a0b01c1aa85f59cb7b1b0924507ba3f0fde50d1f8
+oid sha256:d6591b0975d03ef2b03947332b605790b3b58f62ece54e8ec0a1817fcc2075d9
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4930ab50d16eef8d85da54c9a267fe9bccb1ada8d6a69507ea0e2cb66b9e22d
+oid sha256:e88065188cd3ab7e12d28723da8a9b493eccc60528581a8db53ed77ed18ce7bc
 size 15984

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007730464472073697,
+  "epoch": 0.0011595696708110545,
   "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": 270.559,
       "eval_steps_per_second": 33.82,
       "step": 6
+    },
+    {
+      "epoch": 0.0009018875217419313,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 2.8677,
+      "step": 7
+    },
+    {
+      "epoch": 0.0010307285962764929,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 2.7432,
+      "step": 8
+    },
+    {
+      "epoch": 0.0011595696708110545,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 3.1043,
+      "step": 9
+    },
+    {
+      "epoch": 0.0011595696708110545,
+      "eval_loss": 3.1917941570281982,
+      "eval_runtime": 48.3935,
+      "eval_samples_per_second": 270.119,
+      "eval_steps_per_second": 33.765,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 666420413202432.0,
+  "total_flos": 999630619803648.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null