Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1723d01ce24d971f62ea48862a0a37f5374749bb447c5476496b0f9c142753
+oid sha256:d88bcc6395f0d510811e42b166748e9b9dfa3c199f8a5dc055add965a9f14533
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676e8f07a7a19ff56e2cb1c80802de090e9ab0fc592fe12b6a3de424395d8113
+oid sha256:907e832f4fa9407ac43cb9b73dcdec990eb83b4cdf8b2280c4d7fd827bea7fe1
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9e5c0c831587c3533d61cb36995aac83a9f40922ce4df496a867bb67d84b7e
+oid sha256:eb39198e1c03ba0971e8b1588d211a6c43121869b71254d225961454badbceb1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a47c057106d2ddc8c27b996cfcdb012431f97bae35e43b5668738d196070d4
+oid sha256:535bb91ea586ea928fe6012763740a2245e4922b02b18519cc231e354a7d01a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2807017543859649,
+  "epoch": 0.5614035087719298,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 9.954,
       "eval_steps_per_second": 2.566,
       "step": 4
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": NaN,
+      "learning_rate": 8.742553740855506e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": NaN,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": NaN,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": NaN,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "eval_loss": NaN,
+      "eval_runtime": 9.7423,
+      "eval_samples_per_second": 9.957,
+      "eval_steps_per_second": 2.566,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.94769505983529e+16,
+  "total_flos": 1.789539011967058e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null