Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09c46a5ba1443dd62e0bd357fbc3fe6f4b309b31ed69f61d93ce50ce6c85c48
+oid sha256:17bde3c39675eca3b6d99a7636c466b5d0717723b248cdc830b2e3bbf413c5fb
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104e1c37506465c4318bc464b5c1cec428a04acb6fbe4e4dd43143b1dc5d8e85
+oid sha256:47deed054b288db6745aa5dc60b11dab2cf9ed4ba2aec5f5d759ce0382257991
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252d84a8621f0d8623f524bb8ee54bb1a386d75c0645fcaf9bbfcc4b59877fc1
+oid sha256:5a73f4ec8cc461fdcad0bea4ca4995104cb70648550f70c0efd1720de2eef3ad
 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,
@@ -217,6 +217,48 @@
       "eval_samples_per_second": 21.829,
       "eval_steps_per_second": 5.457,
       "step": 750
+    },
+    {
+      "epoch": 6.203025866276232,
+      "grad_norm": 195982.890625,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 829.7355,
+      "step": 800
+    },
+    {
+      "epoch": 6.203025866276232,
+      "eval_runtime": 19.7721,
+      "eval_samples_per_second": 21.849,
+      "eval_steps_per_second": 5.462,
+      "step": 800
+    },
+    {
+      "epoch": 6.593460224499756,
+      "grad_norm": 427655.71875,
+      "learning_rate": 3.359375e-05,
+      "loss": 684.6569,
+      "step": 850
+    },
+    {
+      "epoch": 6.593460224499756,
+      "eval_runtime": 19.7731,
+      "eval_samples_per_second": 21.848,
+      "eval_steps_per_second": 5.462,
+      "step": 850
+    },
+    {
+      "epoch": 6.98389458272328,
+      "grad_norm": 516619.03125,
+      "learning_rate": 2.96875e-05,
+      "loss": 778.275,
+      "step": 900
+    },
+    {
+      "epoch": 6.98389458272328,
+      "eval_runtime": 19.7592,
+      "eval_samples_per_second": 21.863,
+      "eval_steps_per_second": 5.466,
+      "step": 900
     }
   ],
   "logging_steps": 50,