Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b2bddce265096c75430d1aab690c9e5ef3c1d8fa621d6133827aa635911b3d
+oid sha256:319d0771f9f6478abf39f6fbdb71f9b80acb010d10e683952c18c6d1f642be01
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ce7d9b7aafde28a7a3a4beab568854bfb1478d3e5dd92891b775bd71d0630e
+oid sha256:3badad88f69bea5345da4686fad1db6702958c3dc8153c26943392674dd72d5a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47215f12a9f5233c98d1603d926eb0ed071441b4e296c12157e6bb45a04447c6
+oid sha256:1c21f1e8963850e1607a593441f015060ba1737d9f8faeea3a3f2c20615b922a
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23785020011435107,
+  "epoch": 0.30493615399275775,
   "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": 10.081,
       "eval_steps_per_second": 2.527,
       "step": 39
+    },
+    {
+      "epoch": 0.24394892319420622,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3479617.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.25004764627406134,
+      "grad_norm": NaN,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 128837.9375,
+      "step": 41
+    },
+    {
+      "epoch": 0.25614636935391655,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6948.2617,
+      "step": 42
+    },
+    {
+      "epoch": 0.2622450924337717,
+      "grad_norm": NaN,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 523.4606,
+      "step": 43
+    },
+    {
+      "epoch": 0.26834381551362685,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1441023.375,
+      "step": 44
+    },
+    {
+      "epoch": 0.274442538593482,
+      "grad_norm": NaN,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 355334.4688,
+      "step": 45
+    },
+    {
+      "epoch": 0.28054126167333715,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5372089.5,
+      "step": 46
+    },
+    {
+      "epoch": 0.2866399847531923,
+      "grad_norm": NaN,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11815001.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.29273870783304745,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 391988.4688,
+      "step": 48
+    },
+    {
+      "epoch": 0.2988374309129026,
+      "grad_norm": NaN,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3337463.5,
+      "step": 49
+    },
+    {
+      "epoch": 0.30493615399275775,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 30450.1934,
+      "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": 8.724002683339407e+17,
+  "total_flos": 1.1184618824794112e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null