Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0658507901e47a1e081e2301e0186a70659dfde4aff7e134ef8412a196e54b86
+oid sha256:d32a18b0785d783b8f7ca68824fdec9d9a5c5f53e5ad57b00c7655d6e20ec21a
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1a6161b8cd8bad5f97beb9334e870db02a25dc2cceea6bf6e8548be9b91bb0
+oid sha256:26f5f20bc83ebedde1ae0dac318d82eccf4ac037d79e876f524681ea47ac2bd3
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0ec4d2188868fd24263efa2856258953fca7ad21aed2b50e22b491f1d8939f
+oid sha256:c4b34564e8f5056ecea4875b26da43b7e79461939fc193402ad477fba74d3da7
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a902ca58dea28be10847ac21293e6d27c44fc74bd49d763b881d90cbd1e58f0a
+oid sha256:af2a155e857e9182a60853ae072465deebfe720a1b7475fedfc54c31656178bc
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7038535984515221,
+  "epoch": 0.8798169980644026,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,6 +296,78 @@
       "eval_samples_per_second": 107.707,
       "eval_steps_per_second": 4.144,
       "step": 4000
+    },
+    {
+      "epoch": 0.7258490234031322,
+      "grad_norm": 1.0874834060668945,
+      "learning_rate": 0.00022743269399964805,
+      "loss": 3.254,
+      "step": 4125
+    },
+    {
+      "epoch": 0.7478444483547422,
+      "grad_norm": 0.6965116262435913,
+      "learning_rate": 0.00022523315150448702,
+      "loss": 3.2525,
+      "step": 4250
+    },
+    {
+      "epoch": 0.7698398733063523,
+      "grad_norm": 0.6829759478569031,
+      "learning_rate": 0.00022303360900932605,
+      "loss": 3.2502,
+      "step": 4375
+    },
+    {
+      "epoch": 0.7918352982579624,
+      "grad_norm": 0.7037951946258545,
+      "learning_rate": 0.00022083406651416505,
+      "loss": 3.2419,
+      "step": 4500
+    },
+    {
+      "epoch": 0.7918352982579624,
+      "eval_loss": 2.7353272438049316,
+      "eval_runtime": 90.7352,
+      "eval_samples_per_second": 108.558,
+      "eval_steps_per_second": 4.177,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8138307232095724,
+      "grad_norm": 0.9032262563705444,
+      "learning_rate": 0.00021863452401900402,
+      "loss": 3.2426,
+      "step": 4625
+    },
+    {
+      "epoch": 0.8358261481611825,
+      "grad_norm": 0.6463780403137207,
+      "learning_rate": 0.00021643498152384302,
+      "loss": 3.2408,
+      "step": 4750
+    },
+    {
+      "epoch": 0.8578215731127925,
+      "grad_norm": 0.8066023588180542,
+      "learning_rate": 0.00021423543902868202,
+      "loss": 3.2178,
+      "step": 4875
+    },
+    {
+      "epoch": 0.8798169980644026,
+      "grad_norm": 0.7497230172157288,
+      "learning_rate": 0.000212035896533521,
+      "loss": 3.2268,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8798169980644026,
+      "eval_loss": 2.721640110015869,
+      "eval_runtime": 90.4581,
+      "eval_samples_per_second": 108.89,
+      "eval_steps_per_second": 4.19,
+      "step": 5000
     }
   ],
   "logging_steps": 125,
@@ -315,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2346851500032000.0,
+  "total_flos": 2933564375040000.0,
   "train_batch_size": 26,
   "trial_name": null,
   "trial_params": null