Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d1c0b449d8cc304f50f3f201af4ed5c2e4f2fea7440d183f185823bfe13a27a
+oid sha256:8e2d9d2481013df410245d95eb76e42f5bf1d25dcea3127643adecd87071ee6f
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c1f55371333665004b075b79b96c0d1ddf708f5b5cc1c187b67e26fdd2631f
+oid sha256:89c8a0cc32b08859b177bb4e34222424d3b33f66b6dcaa753f4bd551adb5ece4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01606425702811245,
+  "epoch": 0.020595201318092886,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 12.287,
       "eval_steps_per_second": 6.149,
       "step": 39
+    },
+    {
+      "epoch": 0.016476161054474307,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.016888065080836165,
+      "grad_norm": NaN,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.017299969107198023,
+      "grad_norm": NaN,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 1.0405,
+      "step": 42
+    },
+    {
+      "epoch": 0.01771187313355988,
+      "grad_norm": NaN,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.8838,
+      "step": 43
+    },
+    {
+      "epoch": 0.01812377715992174,
+      "grad_norm": NaN,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.018535681186283594,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.018947585212645453,
+      "grad_norm": NaN,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.4555,
+      "step": 46
+    },
+    {
+      "epoch": 0.01935948923900731,
+      "grad_norm": NaN,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.01977139326536917,
+      "grad_norm": NaN,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.020183297291731028,
+      "grad_norm": NaN,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.020595201318092886,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0721,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.171608990167859e+16,
+  "total_flos": 2.7489812216807424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null