Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8c1702bdc50caa24c8a258da594cb48758fb79a4c9fee4b6d2a0aa0c8a3d1e
+oid sha256:9b2449d036e321d75029d8a603b7ec82ea56a1879ce0d9c7638a3dba7df98c52
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cbd472dfcbe29ea3fd9793832b50ed72d30227351ae08534f1ab2ad69654cae
+oid sha256:ae1a7590c797c9f1d40294cfce6ffb400b297dc67bf1d6c158f9069f9c76d25f
 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": 21.818,
       "eval_steps_per_second": 5.454,
       "step": 1000
+    },
+    {
+      "epoch": 8.140556368960468,
+      "grad_norm": 406190.0625,
+      "learning_rate": 1.796875e-05,
+      "loss": 536.1774,
+      "step": 1050
+    },
+    {
+      "epoch": 8.140556368960468,
+      "eval_runtime": 19.767,
+      "eval_samples_per_second": 21.855,
+      "eval_steps_per_second": 5.464,
+      "step": 1050
+    },
+    {
+      "epoch": 8.530990727183992,
+      "grad_norm": 325491.78125,
+      "learning_rate": 1.4062500000000001e-05,
+      "loss": 373.9504,
+      "step": 1100
+    },
+    {
+      "epoch": 8.530990727183992,
+      "eval_runtime": 19.7611,
+      "eval_samples_per_second": 21.861,
+      "eval_steps_per_second": 5.465,
+      "step": 1100
+    },
+    {
+      "epoch": 8.921425085407517,
+      "grad_norm": 98692.546875,
+      "learning_rate": 1.0156250000000001e-05,
+      "loss": 313.6299,
+      "step": 1150
+    },
+    {
+      "epoch": 8.921425085407517,
+      "eval_runtime": 19.766,
+      "eval_samples_per_second": 21.856,
+      "eval_steps_per_second": 5.464,
+      "step": 1150
     }
   ],
   "logging_steps": 50,