Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca6d80fdb6b06900b16612d724e8387d91f681cbc15771837666fa89c46b3ce4
+oid sha256:598e927453b7a81cf2046927a6420bd0d8c6254aee6389e737d362fd88b5a2aa
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb22c85dfbc20aa45d4b5c97669f2a88c9102e142b0f1bd4f0ad19181f33e67
+oid sha256:aa4f92032ca04fd8a42705220f7b2aff476a8d37a0978772d6d759aee5a8f74d
 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": 0.7964601769911505,
+  "epoch": 0.8761061946902655,
   "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": 36.189,
       "eval_steps_per_second": 4.571,
       "step": 90
+    },
+    {
+      "epoch": 0.8230088495575221,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.8495575221238938,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.8761061946902655,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.8761061946902655,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2548,
+      "eval_samples_per_second": 36.158,
+      "eval_steps_per_second": 4.567,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.44930257616896e+16,
+  "total_flos": 2.694232833785856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null