Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d680bf864856f9bfa584eb3208b4e38f5e9cb6cd1f58cceb049b31b9b2acfd73
+oid sha256:70439eb5bf332bcd85707ea7476cfef47e0adebfd07fc1da5b88b03fbf4caadf
 size 1625426996

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2cfa1bc4665664041205554f346f8cb1719a2a51264588c21beb85644ae889
-size 3250759951
+oid sha256:d3b14d4fda53cf28bf2ae0b4b157bbbff1bcea19560574e1fc479b6280edaaf6
+size 3250745679

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73c7f3308641c8e2c15d99e5247e6be2d37417c7acb4a7ad64cb68b6d5fa4d2
-size 14244
+oid sha256:8ecb6385e3487dcbb2407131ebc74d6528cbf0cd32b5abf0b470cfecc01787ff
+size 13990

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b776a4dee12abf784324330625ce24646d6dfd2b7e10e3f7907e7112d9954c0
+oid sha256:3f13c29da6cf7e87c7b07f9b274343bdf230f8df79285a1204e1a03eb02196fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,125 +1,33 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 0.1,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.2,
-      "learning_rate": 1.869158878504673e-05,
-      "loss": 0.4912,
+      "epoch": 0.1,
+      "learning_rate": 4.836557705136758e-05,
+      "loss": 0.3773,
       "step": 500
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 1.7356475300400533e-05,
-      "loss": 0.3659,
-      "step": 1000
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 1.602136181575434e-05,
-      "loss": 0.3266,
-      "step": 1500
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 1.4686248331108147e-05,
-      "loss": 0.2493,
-      "step": 2000
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 1.335113484646195e-05,
-      "loss": 0.2199,
-      "step": 2500
-    },
-    {
-      "epoch": 1.0,
-      "eval_loss": 1.8119621276855469,
-      "eval_runtime": 912.5828,
-      "eval_samples_per_second": 1.369,
-      "eval_steps_per_second": 0.172,
-      "step": 2500
-    },
-    {
-      "epoch": 1.2,
-      "learning_rate": 1.2016021361815755e-05,
-      "loss": 0.1937,
-      "step": 3000
-    },
-    {
-      "epoch": 1.4,
-      "learning_rate": 1.068090787716956e-05,
-      "loss": 0.1332,
-      "step": 3500
-    },
-    {
-      "epoch": 1.6,
-      "learning_rate": 9.345794392523365e-06,
-      "loss": 0.1551,
-      "step": 4000
-    },
-    {
-      "epoch": 1.8,
-      "learning_rate": 8.01068090787717e-06,
-      "loss": 0.1196,
-      "step": 4500
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 6.675567423230975e-06,
-      "loss": 0.1398,
-      "step": 5000
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 2.2787365913391113,
-      "eval_runtime": 910.7781,
-      "eval_samples_per_second": 1.371,
-      "eval_steps_per_second": 0.172,
-      "step": 5000
-    },
-    {
-      "epoch": 2.2,
-      "learning_rate": 5.34045393858478e-06,
-      "loss": 0.1012,
-      "step": 5500
-    },
-    {
-      "epoch": 2.4,
-      "learning_rate": 4.005340453938585e-06,
-      "loss": 0.1021,
-      "step": 6000
-    },
-    {
-      "epoch": 2.6,
-      "learning_rate": 2.67022696929239e-06,
-      "loss": 0.0804,
-      "step": 6500
-    },
-    {
-      "epoch": 2.8,
-      "learning_rate": 1.335113484646195e-06,
-      "loss": 0.0613,
-      "step": 7000
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 0.0,
-      "loss": 0.0713,
-      "step": 7500
+      "epoch": 0.1,
+      "eval_loss": 0.08091682195663452,
+      "eval_runtime": 6249.7001,
+      "eval_samples_per_second": 0.2,
+      "eval_steps_per_second": 0.05,
+      "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7500,
+  "max_steps": 15000,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.26966087401472e+16,
+  "total_flos": 2167104602112000.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8fd0438f41dd769275a8c7c436204a3b8383bf6d9589567415d61a8711569b
+oid sha256:174bd78d776d79859d6c59d304c2b807ab06208a61976a9d5cfc4028cb675643
 size 4536