Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32a18b0785d783b8f7ca68824fdec9d9a5c5f53e5ad57b00c7655d6e20ec21a
+oid sha256:3fd29ac343b2e0582fb8a887937c055cdcc418a58a57805fd2e8f97c4a9b5902
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f5f20bc83ebedde1ae0dac318d82eccf4ac037d79e876f524681ea47ac2bd3
+oid sha256:0f959a9f93fe8c29de8bad80e922cd938a2f1ded943f2da2478b6fa5c4adfd70
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b34564e8f5056ecea4875b26da43b7e79461939fc193402ad477fba74d3da7
+oid sha256:019869f04ad9e65816198cf9bbc88e01065d43c5ae26d3c4dfa75569351f838e
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2a155e857e9182a60853ae072465deebfe720a1b7475fedfc54c31656178bc
+oid sha256:a377768ec214c80211f84cf49de0b3a1987fbbc2efbe16a70dc0f558f050f0a7
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8798169980644026,
+  "epoch": 1.055780397677283,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -368,6 +368,78 @@
       "eval_samples_per_second": 108.89,
       "eval_steps_per_second": 4.19,
       "step": 5000
+    },
+    {
+      "epoch": 0.9018124230160127,
+      "grad_norm": 0.6645826101303101,
+      "learning_rate": 0.00020983635403836,
+      "loss": 3.1946,
+      "step": 5125
+    },
+    {
+      "epoch": 0.9238078479676227,
+      "grad_norm": 0.7062675952911377,
+      "learning_rate": 0.00020763681154319902,
+      "loss": 3.2228,
+      "step": 5250
+    },
+    {
+      "epoch": 0.9458032729192328,
+      "grad_norm": 0.7374680638313293,
+      "learning_rate": 0.000205437269048038,
+      "loss": 3.1905,
+      "step": 5375
+    },
+    {
+      "epoch": 0.9677986978708428,
+      "grad_norm": 0.853108286857605,
+      "learning_rate": 0.000203237726552877,
+      "loss": 3.2011,
+      "step": 5500
+    },
+    {
+      "epoch": 0.9677986978708428,
+      "eval_loss": 2.714653491973877,
+      "eval_runtime": 90.854,
+      "eval_samples_per_second": 108.416,
+      "eval_steps_per_second": 4.172,
+      "step": 5500
+    },
+    {
+      "epoch": 0.9897941228224529,
+      "grad_norm": 0.6738927364349365,
+      "learning_rate": 0.000201038184057716,
+      "loss": 3.1888,
+      "step": 5625
+    },
+    {
+      "epoch": 1.011789547774063,
+      "grad_norm": 0.7420991659164429,
+      "learning_rate": 0.00019883864156255496,
+      "loss": 3.1835,
+      "step": 5750
+    },
+    {
+      "epoch": 1.0337849727256732,
+      "grad_norm": 0.8556201457977295,
+      "learning_rate": 0.00019663909906739396,
+      "loss": 3.1885,
+      "step": 5875
+    },
+    {
+      "epoch": 1.055780397677283,
+      "grad_norm": 0.7332561016082764,
+      "learning_rate": 0.00019443955657223294,
+      "loss": 3.1691,
+      "step": 6000
+    },
+    {
+      "epoch": 1.055780397677283,
+      "eval_loss": 2.692098617553711,
+      "eval_runtime": 90.3724,
+      "eval_samples_per_second": 108.993,
+      "eval_steps_per_second": 4.194,
+      "step": 6000
     }
   ],
   "logging_steps": 125,
@@ -387,7 +459,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2933564375040000.0,
+  "total_flos": 3520096723009536.0,
   "train_batch_size": 26,
   "trial_name": null,
   "trial_params": null