Training in progress, step 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88bcc6395f0d510811e42b166748e9b9dfa3c199f8a5dc055add965a9f14533
+oid sha256:9c14ef72fd930c73fbc26fc3420f1b13c63ccc5b96332055eb2b47ecef33f2f7
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907e832f4fa9407ac43cb9b73dcdec990eb83b4cdf8b2280c4d7fd827bea7fe1
+oid sha256:d4515356287d7544b602531ccc5d9e82fedf8697d8579f0210c6ad36102f54d5
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb39198e1c03ba0971e8b1588d211a6c43121869b71254d225961454badbceb1
+oid sha256:57d755f308498f85f0bf5b34c1f0b82fee5222b27e276699047f6c6be77c0807
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535bb91ea586ea928fe6012763740a2245e4922b02b18519cc231e354a7d01a3
+oid sha256:e59b38b7699f7635523e7ab6d478b4e9b420f110d0bbbef9f4bd629aa3d6cd28
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5614035087719298,
+  "epoch": 0.8421052631578947,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 9.957,
       "eval_steps_per_second": 2.566,
       "step": 8
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": NaN,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": NaN,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": NaN,
+      "eval_runtime": 9.752,
+      "eval_samples_per_second": 9.947,
+      "eval_steps_per_second": 2.564,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.789539011967058e+17,
+  "total_flos": 2.684308517950587e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null