Training in progress, step 80, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c857ff19b5adf50a631790577a8b8f083a3e860d43c11647116022c57f2400
+oid sha256:63489c1e38f1ac5a2629813f26123fa744473881124f9e98887d7060c3c099d6
 size 4990951248

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea117d3be8b7f606e8f0df9669b9674cc0c177a3f41530fb4b49852d281cf709
+oid sha256:8d1646b92d5f7acc41fc74dccc5ebd7e37ff62d6dd42249826fea2808dd90f21
 size 559197598

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5d994bd5a403db564d2e586df727af1e1a8965b708a077ea1ebf9d3b171c7d
+oid sha256:daebfbcaf4226179e95a7a2928839a94f01a317bcb32a0021d250f6a3602bfce
 size 5640674860

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee79d800c9a2e264a65d6a3737f4962e778c9d7f80d6768b8edca0eab21c8a92
+oid sha256:d37ebc224a7a4705cea1613dd8fd1f8f471218f082721f531c7167abec9ee3a5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bca44b3406787bbe774f3a29ce0829dfb77a865b68b27b9e43acbe4e5eed16c
+oid sha256:ce78d042223b902aa422256a43e83b469f7892bf3a43f13e3a19d2fa900c9406
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c4501abe63013597d8ae9d4d94b5d2a3244495e565f60cd63e4d4ed904ecf9
+oid sha256:f719e5477984d5abea386f4b60be21f4d2ad98970ac0de30ce8a64b3cdb8cb02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38c27a3df45459b9e8441485927824c74e0caf5211147ff5b4d04031c0e3ce9
+oid sha256:97ed4133b2ea99a43dbced219876975f15888ea761a0db49a0afa3f636f6ca78
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73474ac15ab1f9e7ff2dbea9beffe9a6867347710a3cf2ee966c6a4a98243bef
+oid sha256:776a540436bd1dedef12a8b7642374faac449931a1c15952fb54741875421490
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.935483870967742,
+  "epoch": 2.5806451612903225,
   "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": 74.057,
       "eval_steps_per_second": 3.108,
       "step": 60
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 7.15625,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 2.776,
+      "step": 70
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 39.5,
+      "learning_rate": 0.0001934564464599461,
+      "loss": 2.3915,
+      "step": 80
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "eval_loss": 2.7726891040802,
+      "eval_runtime": 20.3002,
+      "eval_samples_per_second": 73.94,
+      "eval_steps_per_second": 3.103,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.679291653377229e+16,
+  "total_flos": 6.236887688885043e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null