Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c66332e59cca97abe5c785353e5feee48aa5aa0f7ac95ed66e78d5c2b1434c49
+oid sha256:61fb5b78cc5a167482399cc97c87bcf903f86a4c8bd69daadaebb13589e5a57b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f66835807e11da9f24126ef7d8a45e8848ee013ec7bfae08973c9be9aa9f73
+oid sha256:f0fa753fb951b0fd819d629c13f53f36a173271d4758904221c7092e57242a05
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004854486759387364,
+  "epoch": 0.009708973518774727,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 28.135,
       "eval_steps_per_second": 14.071,
       "step": 50
+    },
+    {
+      "epoch": 0.005825384111264836,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.00679628146314231,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 331.5758,
+      "step": 70
+    },
+    {
+      "epoch": 0.007767178815019782,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.008738076166897256,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 5.5299,
+      "step": 90
+    },
+    {
+      "epoch": 0.009708973518774727,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 1.023,
+      "step": 100
+    },
+    {
+      "epoch": 0.009708973518774727,
+      "eval_loss": NaN,
+      "eval_runtime": 154.0904,
+      "eval_samples_per_second": 28.146,
+      "eval_steps_per_second": 14.076,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0340757676228608e+16,
+  "total_flos": 2.1163499820417024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null