Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17bde3c39675eca3b6d99a7636c466b5d0717723b248cdc830b2e3bbf413c5fb
+oid sha256:9d8c1702bdc50caa24c8a258da594cb48758fb79a4c9fee4b6d2a0aa0c8a3d1e
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47deed054b288db6745aa5dc60b11dab2cf9ed4ba2aec5f5d759ce0382257991
+oid sha256:7cbd472dfcbe29ea3fd9793832b50ed72d30227351ae08534f1ab2ad69654cae
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a73f4ec8cc461fdcad0bea4ca4995104cb70648550f70c0efd1720de2eef3ad
+oid sha256:f75193245e65869ca07a16a2caab41ba86286fcae28542136bb36df639a39935
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1318a37534b462ff16790cf62c003bcdfdf0493594d4a0b3e928e4d2f7999ab
+oid sha256:98b9a9b66ad7c2c92d26ff031cce36ce8f9c2ebdb6be883784d837b0e0137568
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 50,
-  "global_step": 903,
+  "global_step": 1032,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,34 @@
       "eval_samples_per_second": 21.863,
       "eval_steps_per_second": 5.466,
       "step": 900
+    },
+    {
+      "epoch": 7.367008296730113,
+      "grad_norm": 240667.90625,
+      "learning_rate": 2.578125e-05,
+      "loss": 658.1772,
+      "step": 950
+    },
+    {
+      "epoch": 7.367008296730113,
+      "eval_runtime": 19.7525,
+      "eval_samples_per_second": 21.871,
+      "eval_steps_per_second": 5.468,
+      "step": 950
+    },
+    {
+      "epoch": 7.7574426549536355,
+      "grad_norm": 319554.6875,
+      "learning_rate": 2.1875e-05,
+      "loss": 457.791,
+      "step": 1000
+    },
+    {
+      "epoch": 7.7574426549536355,
+      "eval_runtime": 19.8005,
+      "eval_samples_per_second": 21.818,
+      "eval_steps_per_second": 5.454,
+      "step": 1000
     }
   ],
   "logging_steps": 50,