Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e59169943b54be3d7eb668ac02f8339930bf6e79a5c68e753ed0aa42ee977cf
+oid sha256:12fc2fc95519e8c736ec6b3d0a77b3e25ed7c233e27f177ff101c766e80bf02b
 size 2609498088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27fd22fb01fb9d40757c9c0d63833bd578ba1318c457743f1a5a8903b43a67f
+oid sha256:4c942f7fe65abeb2bdc8fc7396b9a17cc51c747caca3939743aa338298ee7e1d
 size 5208796146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d42a1f1fae69ab6dd8627554c9be0722476204fd05dc463f39ae8915d82e67f
+oid sha256:d9bd9a69f693e1a28c165ba6f898faeebbcaaab424a68e8c32fc40b36b9ff5e3
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebd3960ec1614497d0e6e97cebd857464e618edc4df8a50eee43da5ac2ba348
+oid sha256:f1318a37534b462ff16790cf62c003bcdfdf0493594d4a0b3e928e4d2f7999ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.0,
+  "epoch": 7.0,
   "eval_steps": 50,
-  "global_step": 774,
+  "global_step": 903,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,51 @@
       "eval_samples_per_second": 37.545,
       "eval_steps_per_second": 18.772,
       "step": 750
+    },
+    {
+      "epoch": 6.203025866276232,
+      "grad_norm": 0.6937867403030396,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.0941,
+      "step": 800
+    },
+    {
+      "epoch": 6.203025866276232,
+      "eval_loss": 1.2105975151062012,
+      "eval_runtime": 11.55,
+      "eval_samples_per_second": 37.403,
+      "eval_steps_per_second": 18.701,
+      "step": 800
+    },
+    {
+      "epoch": 6.593460224499756,
+      "grad_norm": 0.719428300857544,
+      "learning_rate": 3.359375e-05,
+      "loss": 1.0923,
+      "step": 850
+    },
+    {
+      "epoch": 6.593460224499756,
+      "eval_loss": 1.1799763441085815,
+      "eval_runtime": 11.536,
+      "eval_samples_per_second": 37.448,
+      "eval_steps_per_second": 18.724,
+      "step": 850
+    },
+    {
+      "epoch": 6.98389458272328,
+      "grad_norm": 0.65595942735672,
+      "learning_rate": 2.96875e-05,
+      "loss": 1.0796,
+      "step": 900
+    },
+    {
+      "epoch": 6.98389458272328,
+      "eval_loss": 1.1729077100753784,
+      "eval_runtime": 11.5363,
+      "eval_samples_per_second": 37.447,
+      "eval_steps_per_second": 18.724,
+      "step": 900
     }
   ],
   "logging_steps": 50,
@@ -251,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.139790752224379e+17,
+  "total_flos": 2.4964225415774208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null