Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd264370ec8116c7637706c9258994699d14569d41d8da7845c334f7b50ce369
+oid sha256:f6e10bf400529e94f432815385ce44f8e973a32eec3c9be3ec7acb4befb5dddb
 size 4140280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a896c905ae2851fd5619a41bac6532997acf6e410f4b5d3b8f4e5551100aa7
+oid sha256:d025fb3332edbb7be7f811c4700970dac0a63ff9085905c32fab3d64583bd4c1
 size 4291766

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55dcddf95f6df626baaef418beac8e8ae2cf66b3e94fecb344f33442737e8951
+oid sha256:4d808c6b7b18375173160ea5614f4474ba68bfdb4e4128fb96aa9c3edc2450cb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64d4aece2607f1d3bc7ea4374d4260437623a49135c05801f0d688b2e80f254
+oid sha256:df89f21b55b2d65718ed1d2cdeadc1ff16958bc5f6ac66f1e557ef70c9dfe8e2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c21f77637fb3f56ba02ef509b8a471991cc2ccccca6af51847140ee757415a
+oid sha256:de0d61bbd2d2279b9ea09ac3613573a205fb5f5a279324183ce6c23ca8fbac77
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6687608b07c4a2d2152b65f49fc8bc54d8b4fc77151984b62a1a90d271ed6a0
+oid sha256:aec03eba7d44b82e794b52483557f97fad5167bb70a3cf0811cfd3a0a2764f32
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f299ab56b5f200cab03608b3ac75cf1761ca29c2207c1dfe5ab919b66f8dbd88
+oid sha256:c420644371984c0c279fff13e73e1c3067315dc564ce90ee02e2ca237d8a9e35
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 13.333333333333334,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 646.34,
       "eval_steps_per_second": 5.167,
       "step": 60
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 0.4609375,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 9.9373,
+      "step": 70
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.462890625,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 9.9182,
+      "step": 80
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 9.922646522521973,
+      "eval_runtime": 2.3435,
+      "eval_samples_per_second": 640.486,
+      "eval_steps_per_second": 5.12,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 98617817825280.0,
+  "total_flos": 131490423767040.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null