Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5d9be0c5d559f23742ab958ed7b2b40e5d0e7499e22b9c05afe7c8d903d767
+oid sha256:44848cadf31f5b5aa65acb2471e5846a9f0b179655cab5aef9a9f5ded8dbfd54
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b68b5ba54bdbf8baa3d26a7490acac1193a5b5381d147f873c74e6bb65e1a01
+oid sha256:defcb80747ee30b333462e71ae2dd00e362287da4762ee797531308498ebed1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3235294117647058,
+  "epoch": 1.4558823529411764,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 6.825,
       "eval_steps_per_second": 0.89,
       "step": 90
+    },
+    {
+      "epoch": 1.3676470588235294,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.6242,
+      "step": 93
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.3084,
+      "step": 96
+    },
+    {
+      "epoch": 1.4558823529411764,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.4601,
+      "step": 99
+    },
+    {
+      "epoch": 1.4558823529411764,
+      "eval_loss": NaN,
+      "eval_runtime": 16.8479,
+      "eval_samples_per_second": 6.826,
+      "eval_steps_per_second": 0.89,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5531788706185216e+17,
+  "total_flos": 2.8091188339802112e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null