Training in progress, step 84, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d51033c27da30a5adb7a850762d265e311f59865b108cd781deadf531e5298d
+oid sha256:3f290fa243f85ebc3e1e0011171484889deffd1306f8be27e8e7d564ecd9f73b
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff5ccbaf93630d7af16d8aab12fb1d572eec18da64a913ba8affabb15689673
+oid sha256:78d0e70adf74bf6b338edf706234f05e3af307576a2e4abcf4df30d3fec84b78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24225e147d7b9425c760fd15a44cb007389a8d29dfe49f25bc43f19fd631f65
+oid sha256:2df224011d0e75c4a97901f6c1b2930bba4bc3a9aa7c877e6c91e796bec6013f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002232231833220393,
+  "epoch": 0.004464463666440786,
   "eval_steps": 42,
-  "global_step": 42,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,112 @@
       "eval_samples_per_second": 13.368,
       "eval_steps_per_second": 1.671,
       "step": 42
+    },
+    {
+      "epoch": 0.002391676964164707,
+      "grad_norm": NaN,
+      "learning_rate": 9.874639560909117e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0025511220951090208,
+      "grad_norm": NaN,
+      "learning_rate": 9.852339101019574e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0027105672260533346,
+      "grad_norm": NaN,
+      "learning_rate": 9.828243544427796e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.0028700123569976484,
+      "grad_norm": NaN,
+      "learning_rate": 9.802361805155097e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.003029457487941962,
+      "grad_norm": NaN,
+      "learning_rate": 9.774703458011453e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.003188902618886276,
+      "grad_norm": NaN,
+      "learning_rate": 9.745278735053343e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0033483477498305898,
+      "grad_norm": NaN,
+      "learning_rate": 9.714098521798465e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.003507792880774903,
+      "grad_norm": NaN,
+      "learning_rate": 9.681174353198687e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.003667238011719217,
+      "grad_norm": NaN,
+      "learning_rate": 9.64651840937276e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.0038266831426635307,
+      "grad_norm": NaN,
+      "learning_rate": 9.610143511100354e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.003986128273607845,
+      "grad_norm": NaN,
+      "learning_rate": 9.572063115079063e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.004145573404552159,
+      "grad_norm": NaN,
+      "learning_rate": 9.53229130894619e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.0043050185354964726,
+      "grad_norm": NaN,
+      "learning_rate": 9.490842806067095e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.004464463666440786,
+      "grad_norm": NaN,
+      "learning_rate": 9.44773294009206e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.004464463666440786,
+      "eval_loss": NaN,
+      "eval_runtime": 2370.6582,
+      "eval_samples_per_second": 13.367,
+      "eval_steps_per_second": 1.671,
+      "step": 84
     }
   ],
   "logging_steps": 3,
@@ -140,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.373469870201242e+16,
+  "total_flos": 1.278465257987113e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null