Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db377b13142f5a36919ac15fa0671382c2dbd507bcd6d7d6137104e399c8d281
+oid sha256:393a2644c7aa4ab801d34d0b3322301105a7470ff9f2b27807d653beb37fae92
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4826af20fec54c2a431ee9061f16db894f25709fed3896333f2c0c6628949224
+oid sha256:fa9c6e5309374f3fac2522c8f5a0af7e8adfd937dc1a7d93a5248d2f583124da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03453634950785702,
+  "epoch": 0.06907269901571404,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.0359178034881713,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.03729925746848558,
+      "grad_norm": NaN,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.038680711448799865,
+      "grad_norm": NaN,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.040062165429114144,
+      "grad_norm": NaN,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.04144361940942842,
+      "grad_norm": NaN,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0428250733897427,
+      "grad_norm": NaN,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.04420652737005699,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.045587981350371266,
+      "grad_norm": NaN,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.046969435330685545,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.048350889310999824,
+      "grad_norm": NaN,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.04973234329131411,
+      "grad_norm": NaN,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.05111379727162839,
+      "grad_norm": NaN,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.05249525125194267,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.053876705232256954,
+      "grad_norm": NaN,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.05525815921257123,
+      "grad_norm": NaN,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.05663961319288551,
+      "grad_norm": NaN,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.05802106717319979,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.059402521153514076,
+      "grad_norm": NaN,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.060783975133828355,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.062165429114142634,
+      "grad_norm": NaN,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.06354688309445691,
+      "grad_norm": NaN,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.06492833707477119,
+      "grad_norm": NaN,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.06630979105508547,
+      "grad_norm": NaN,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.06769124503539976,
+      "grad_norm": NaN,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.06907269901571404,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.26732322177024e+16,
+  "total_flos": 6.53464644354048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null