Training in progress, step 2800, checkpoint

last-checkpoint/model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e32f3572a879128a25a247a0be200e23f39567f58fd956064c5c68b66cf5b5a9
+oid sha256:899d935b5c5a49d9246d93bb12f53fb2a5d65c9908cc6913af4e648924301803
 size 4840658560

last-checkpoint/model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af444108fd67a3c6e63c47ec8640ec8b500d36ed5bf7b185fccf407ad0527f47
+oid sha256:b447174ff33cd1c0d7a82b337d96f938df8c838d65d6f9fde9fd7985fc02cd93
 size 4857206856

last-checkpoint/model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb92006261485577e7645190694e9087dca6c01dee24ca945f56f7511967919c
+oid sha256:bd870d340d98656a432d2d32968441795a4c6b494ed4ea44a770d0edc35c3865
 size 4857206904

last-checkpoint/model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e2d5176675f79b6e2a0149a55de72ce168b30b40ca8178c6800ec8607f99ac
+oid sha256:2d7dfc7b648b3aa287c824b7feecc82122461caa52be5de3d18dcdd6975ecbbc
 size 4857206904

last-checkpoint/model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e8488c95aae92eb0ae6aa54da0ba180cca2726f5bd061b36b57c208bc2d404
+oid sha256:2d28f9e42e36012953b0ad80e3029216d6abc5eb46b9cc829c31ea903fb7a731
 size 4857206904

last-checkpoint/model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfba0ab5a7de6b7625c5951644381b869990b9cf3bc79c0d13d322d631e496f
+oid sha256:79f8b6e521feebdc5b2b7367c01fd851c314151387cf42e49264cd3b76a86b2b
 size 2684734256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.8,
+  "epoch": 5.6,
   "eval_steps": 50,
-  "global_step": 2400,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,126 @@
       "eval_samples_per_second": 68.983,
       "eval_steps_per_second": 3.538,
       "step": 2400
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.7993331551551819,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 0.1222,
+      "step": 2450
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.9250988364219666,
+      "eval_runtime": 2.4444,
+      "eval_samples_per_second": 63.82,
+      "eval_steps_per_second": 3.273,
+      "step": 2450
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.1892589330673218,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.1186,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.9481778144836426,
+      "eval_runtime": 3.3935,
+      "eval_samples_per_second": 45.97,
+      "eval_steps_per_second": 2.357,
+      "step": 2500
+    },
+    {
+      "epoch": 5.1,
+      "grad_norm": 0.7223986983299255,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 0.0726,
+      "step": 2550
+    },
+    {
+      "epoch": 5.1,
+      "eval_loss": 0.974181056022644,
+      "eval_runtime": 2.9499,
+      "eval_samples_per_second": 52.883,
+      "eval_steps_per_second": 2.712,
+      "step": 2550
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.7545835971832275,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0717,
+      "step": 2600
+    },
+    {
+      "epoch": 5.2,
+      "eval_loss": 0.9890027046203613,
+      "eval_runtime": 2.7635,
+      "eval_samples_per_second": 56.449,
+      "eval_steps_per_second": 2.895,
+      "step": 2600
+    },
+    {
+      "epoch": 5.3,
+      "grad_norm": 1.2251814603805542,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.072,
+      "step": 2650
+    },
+    {
+      "epoch": 5.3,
+      "eval_loss": 0.9911813735961914,
+      "eval_runtime": 2.2537,
+      "eval_samples_per_second": 69.22,
+      "eval_steps_per_second": 3.55,
+      "step": 2650
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.45753681659698486,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.0718,
+      "step": 2700
+    },
+    {
+      "epoch": 5.4,
+      "eval_loss": 0.9854485988616943,
+      "eval_runtime": 2.2539,
+      "eval_samples_per_second": 69.212,
+      "eval_steps_per_second": 3.549,
+      "step": 2700
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 1.0563805103302002,
+      "learning_rate": 1e-05,
+      "loss": 0.072,
+      "step": 2750
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.9962345957756042,
+      "eval_runtime": 2.2507,
+      "eval_samples_per_second": 69.313,
+      "eval_steps_per_second": 3.555,
+      "step": 2750
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.6450284719467163,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0699,
+      "step": 2800
+    },
+    {
+      "epoch": 5.6,
+      "eval_loss": 0.9950909614562988,
+      "eval_runtime": 2.2532,
+      "eval_samples_per_second": 69.235,
+      "eval_steps_per_second": 3.551,
+      "step": 2800
     }
   ],
   "logging_steps": 50,
@@ -734,7 +854,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 400,
-  "total_flos": 1.1589925681181491e+17,
+  "total_flos": 1.3524716052545536e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null