Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b1bad342ac797ae7f8347634a2ce237e847c6a2d60987518225454f9e747ad
+oid sha256:a09c46a5ba1443dd62e0bd357fbc3fe6f4b309b31ed69f61d93ce50ce6c85c48
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adecf4e9e07fee4c38cefd10b01a139c1b07f5ea9611ec0ade4b7a0c54c74f1
+oid sha256:104e1c37506465c4318bc464b5c1cec428a04acb6fbe4e4dd43143b1dc5d8e85
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7c781d03ce544a7aa31375ec1cce20ab821ae066d16219adab4b2436b4176d
+oid sha256:252d84a8621f0d8623f524bb8ee54bb1a386d75c0645fcaf9bbfcc4b59877fc1
 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,
@@ -175,6 +175,48 @@
       "eval_samples_per_second": 21.884,
       "eval_steps_per_second": 5.471,
       "step": 600
+    },
+    {
+      "epoch": 5.039043435822352,
+      "grad_norm": 328730.40625,
+      "learning_rate": 4.921875e-05,
+      "loss": 971.7115,
+      "step": 650
+    },
+    {
+      "epoch": 5.039043435822352,
+      "eval_runtime": 19.734,
+      "eval_samples_per_second": 21.891,
+      "eval_steps_per_second": 5.473,
+      "step": 650
+    },
+    {
+      "epoch": 5.4294777940458765,
+      "grad_norm": 145752.921875,
+      "learning_rate": 4.5312500000000004e-05,
+      "loss": 901.4456,
+      "step": 700
+    },
+    {
+      "epoch": 5.4294777940458765,
+      "eval_runtime": 19.7781,
+      "eval_samples_per_second": 21.842,
+      "eval_steps_per_second": 5.461,
+      "step": 700
+    },
+    {
+      "epoch": 5.819912152269399,
+      "grad_norm": 190886.453125,
+      "learning_rate": 4.140625e-05,
+      "loss": 991.2295,
+      "step": 750
+    },
+    {
+      "epoch": 5.819912152269399,
+      "eval_runtime": 19.7898,
+      "eval_samples_per_second": 21.829,
+      "eval_steps_per_second": 5.457,
+      "step": 750
     }
   ],
   "logging_steps": 50,