Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b046fc1073ac10130a6554de2dc6d82fd6f7d91e8c0405612fe68ad82ad5378
+oid sha256:1e59169943b54be3d7eb668ac02f8339930bf6e79a5c68e753ed0aa42ee977cf
 size 2609498088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bc2e4ec6bdc742f4ad4def66c2207af291f3b87deb4413422c676c78b3b92c
+oid sha256:e27fd22fb01fb9d40757c9c0d63833bd578ba1318c457743f1a5a8903b43a67f
 size 5208796146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321aca7bd350f679df83bd3bdc1330a4f60d8b3c06b22857cf838532bb504c43
+oid sha256:9d42a1f1fae69ab6dd8627554c9be0722476204fd05dc463f39ae8915d82e67f
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b514faa73b6e320d8ae19d93f3da594146e59f1072af645ee09b9ce747afd0a1
+oid sha256:0ebd3960ec1614497d0e6e97cebd857464e618edc4df8a50eee43da5ac2ba348
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 50,
-  "global_step": 645,
+  "global_step": 774,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,51 @@
       "eval_samples_per_second": 37.432,
       "eval_steps_per_second": 18.716,
       "step": 600
+    },
+    {
+      "epoch": 5.039043435822352,
+      "grad_norm": 0.6386131048202515,
+      "learning_rate": 4.921875e-05,
+      "loss": 1.1507,
+      "step": 650
+    },
+    {
+      "epoch": 5.039043435822352,
+      "eval_loss": 1.2271380424499512,
+      "eval_runtime": 11.5699,
+      "eval_samples_per_second": 37.338,
+      "eval_steps_per_second": 18.669,
+      "step": 650
+    },
+    {
+      "epoch": 5.4294777940458765,
+      "grad_norm": 0.6771230101585388,
+      "learning_rate": 4.5312500000000004e-05,
+      "loss": 1.134,
+      "step": 700
+    },
+    {
+      "epoch": 5.4294777940458765,
+      "eval_loss": 1.2191808223724365,
+      "eval_runtime": 11.5238,
+      "eval_samples_per_second": 37.488,
+      "eval_steps_per_second": 18.744,
+      "step": 700
+    },
+    {
+      "epoch": 5.819912152269399,
+      "grad_norm": 0.6427966952323914,
+      "learning_rate": 4.140625e-05,
+      "loss": 1.1258,
+      "step": 750
+    },
+    {
+      "epoch": 5.819912152269399,
+      "eval_loss": 1.2103700637817383,
+      "eval_runtime": 11.5062,
+      "eval_samples_per_second": 37.545,
+      "eval_steps_per_second": 18.772,
+      "step": 750
     }
   ],
   "logging_steps": 50,
@@ -206,7 +251,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7831589615291597e+17,
+  "total_flos": 2.139790752224379e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null