Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea696d2587b1f54d48abd343f4a45febdf70e3200c601331167fb298210e7697
+oid sha256:4c00f4770dc8e7b019dc6a6debaa362bab68c6cfd35eca15267ad109c23a42fe
 size 3671315016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891bb3f74fffb150ee0e4fd64902345a9e4e4c699eeda78a27cc4ddb1ebfdf3f
+oid sha256:3346e3093582358d266962c8edb157180d5be4fa3300662d51e548543c8eb4e4
 size 3730396474

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc7ee943309ed7bb32237991354d697dcd8f95c37aa33d96eaf5b88acabc85e
+oid sha256:2355912033cdf8a210471f65d6956ea7b204dc1f992bb7ff160a01398842e73d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17bab1f66ce950adc6e75df51b00c839acb7dea4ebe9ad88a0a2fa4a2d6f56f6
+oid sha256:7f1df9b508fa40b405b039f0683e8579bc073a168693465fb82192e1ad1fd78d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0fd321d7cb8f46493218b46f09e546f78eb27d0fa570bc1ec1cce83fe583552
+oid sha256:f5502dbebdf9f40b2dd0bbf6873e0329b5b773ddb393ab99bfe392b8af956e80
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48fedec6859d1ea6b2a1e1ad3e74cfd74439c31d6bc650db7d9760dd6bb6443
+oid sha256:deb9b135706ccb81d17045fbd75611752ff5ba7ec0435cca72d7997d0abd01ac
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70a3961c07fb8ffab3e54df3003320b77e92cc985157fe02ca51eb0c3d20421
+oid sha256:66f97637bcae20735f25e4b45c4e868550cd21597f26c3bd0dc18e1466020699
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.086956521739131,
+  "epoch": 6.956521739130435,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 94.253,
       "eval_steps_per_second": 2.951,
       "step": 140
+    },
+    {
+      "epoch": 6.521739130434782,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.1172,
+      "step": 150
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 0.9375,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.1326,
+      "step": 160
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_loss": 3.5411362648010254,
+      "eval_runtime": 15.9272,
+      "eval_samples_per_second": 94.241,
+      "eval_steps_per_second": 2.951,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.395545982795776e+16,
+  "total_flos": 9.594909694623744e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null