Training in progress, step 560, checkpoint

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc81f761cfc8bdce5d4645d596275ebae46f5b388451e19e4c8d7151b84c9715
+oid sha256:9a4b652f70bb7bf6937fc33a7d01c3f03c6342b239ff26ece13523d743f26cd8
 size 4976698672

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7da038dd672630df7e600441c36fa83e824a9e2fb99b73b2420909cbb2ad6eb
+oid sha256:9d9bd27753d862a088993cd46574f25b05c2cda11093f946598dc46956f484d9
 size 4999802720

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e5d26c381151ab0de50104b9e5ce82eabe494b836bd9ed820acb0c36701679
+oid sha256:ed860de1deed7cdc39bd811790ea63ae1b083edeca3b67d013613d748b62c05e
 size 4915916176

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a091b0c39bd9b27ef31e5a41bbc9472016dcf757f5df52524848568afc94178
+oid sha256:a69028f8407cef8ebd9eb20ad7eb1ceb93e80717dfdef9783a0b74dc25525cac
 size 1168138808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e282f5d03b3ef029829e361590621b745fcf0f26c09b36123475b88e1779ed
+oid sha256:941b6102c0e182d11f8867f5507451850e6f35a383ea6b5af7bb2b7ef99c6f80
 size 16311821444

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631bcc7b2b54adc0f8c13ccb364aeb8eebda651c6ce4485857a6aba1f8d727b5
+oid sha256:7de5eba3aed7d95f28e0f9dfb9375531a0dbaceef85a8671b534835ab0e70865
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6669863251bb7520c41ff8dcf5a27af1ba81a55e01b68c96831c6305cf7b27
+oid sha256:a17839f2358f75951188e6934b7a52a31bb75248661d49e4c6ce09414906fd23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13450594930160373,
+  "epoch": 0.14485256078634248,
   "eval_steps": 20,
-  "global_step": 520,
+  "global_step": 560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -587,6 +587,50 @@
       "eval_samples_per_second": 8.776,
       "eval_steps_per_second": 4.388,
       "step": 520
+    },
+    {
+      "epoch": 0.1370926021727884,
+      "grad_norm": 15.1875,
+      "learning_rate": 0.00018598991661526572,
+      "loss": 3.0777,
+      "step": 530
+    },
+    {
+      "epoch": 0.1396792550439731,
+      "grad_norm": 25.0,
+      "learning_rate": 0.00018530718407223974,
+      "loss": 3.3325,
+      "step": 540
+    },
+    {
+      "epoch": 0.1396792550439731,
+      "eval_loss": 2.90164852142334,
+      "eval_runtime": 106.0394,
+      "eval_samples_per_second": 8.11,
+      "eval_steps_per_second": 4.055,
+      "step": 540
+    },
+    {
+      "epoch": 0.14226590791515778,
+      "grad_norm": 13.5625,
+      "learning_rate": 0.00018460952524209355,
+      "loss": 2.5467,
+      "step": 550
+    },
+    {
+      "epoch": 0.14485256078634248,
+      "grad_norm": 13.125,
+      "learning_rate": 0.00018389706219492147,
+      "loss": 3.2562,
+      "step": 560
+    },
+    {
+      "epoch": 0.14485256078634248,
+      "eval_loss": 2.854039192199707,
+      "eval_runtime": 99.183,
+      "eval_samples_per_second": 8.671,
+      "eval_steps_per_second": 4.335,
+      "step": 560
     }
   ],
   "logging_steps": 10,
@@ -606,7 +650,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.590933494431744e+16,
+  "total_flos": 1.0328697609388032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null