Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d7b301c4b6e671939dd23a577ceaa3f157cf1b5ca7ce1d7929079999bb257c3
+oid sha256:d8dabb6381d952326c916117be53ef1632bcb8adcf5513d34c49ab5dc703c54e
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59627224d638a6aee75cb38d5f5279058556b01711f37b49b3ca4a08bdb9be6
+oid sha256:4555c70942753f71d1b1e4a42b999ef15aebf24c06f2a43463e0b20ae30a0caa
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75193245e65869ca07a16a2caab41ba86286fcae28542136bb36df639a39935
+oid sha256:335263bbdf55dec07c081046e09f117f40eceefa6f3b02ab74e94e4a08e084ac
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b9a9b66ad7c2c92d26ff031cce36ce8f9c2ebdb6be883784d837b0e0137568
+oid sha256:17d282d44e6a12e9ca82ec6b42e7f212659678f5fe8c9a58e24a30599040d3e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 50,
-  "global_step": 1032,
+  "global_step": 1161,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,48 @@
       "eval_samples_per_second": 21.995,
       "eval_steps_per_second": 5.499,
       "step": 1000
+    },
+    {
+      "epoch": 8.140556368960468,
+      "grad_norm": 726.1790161132812,
+      "learning_rate": 1.796875e-05,
+      "loss": 1.335,
+      "step": 1050
+    },
+    {
+      "epoch": 8.140556368960468,
+      "eval_runtime": 19.6045,
+      "eval_samples_per_second": 22.036,
+      "eval_steps_per_second": 5.509,
+      "step": 1050
+    },
+    {
+      "epoch": 8.530990727183992,
+      "grad_norm": 391.7787780761719,
+      "learning_rate": 1.4062500000000001e-05,
+      "loss": 1.2137,
+      "step": 1100
+    },
+    {
+      "epoch": 8.530990727183992,
+      "eval_runtime": 19.6376,
+      "eval_samples_per_second": 21.999,
+      "eval_steps_per_second": 5.5,
+      "step": 1100
+    },
+    {
+      "epoch": 8.921425085407517,
+      "grad_norm": 194.22886657714844,
+      "learning_rate": 1.0156250000000001e-05,
+      "loss": 1.1869,
+      "step": 1150
+    },
+    {
+      "epoch": 8.921425085407517,
+      "eval_runtime": 19.647,
+      "eval_samples_per_second": 21.988,
+      "eval_steps_per_second": 5.497,
+      "step": 1150
     }
   ],
   "logging_steps": 50,