Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987cdddaddd6ee9efcbf0406b5dbea003e19c76523f179ea3826ca2f5707f3cd
+oid sha256:0658507901e47a1e081e2301e0186a70659dfde4aff7e134ef8412a196e54b86
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ea40a6da395d8e9289cbe3e64187c17945564d3b3cb832aeaf878ad5504ff8
+oid sha256:8e1a6161b8cd8bad5f97beb9334e870db02a25dc2cceea6bf6e8548be9b91bb0
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7133fcea647449b2caaa65223ebbc0c180189bbd59dbe842634047836d81e2
+oid sha256:3b0ec4d2188868fd24263efa2856258953fca7ad21aed2b50e22b491f1d8939f
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8a8c1f0ca136b116df977b16704d013fad49cab357d7231675ec3945e85ad2
+oid sha256:a902ca58dea28be10847ac21293e6d27c44fc74bd49d763b881d90cbd1e58f0a
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5278901988386415,
+  "epoch": 0.7038535984515221,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -224,6 +224,78 @@
       "eval_samples_per_second": 107.962,
       "eval_steps_per_second": 4.154,
       "step": 3000
+    },
+    {
+      "epoch": 0.5498856237902516,
+      "grad_norm": 0.7471196055412292,
+      "learning_rate": 0.0002450290339609361,
+      "loss": 3.3313,
+      "step": 3125
+    },
+    {
+      "epoch": 0.5718810487418617,
+      "grad_norm": 0.7734588384628296,
+      "learning_rate": 0.00024282949146577507,
+      "loss": 3.3004,
+      "step": 3250
+    },
+    {
+      "epoch": 0.5938764736934717,
+      "grad_norm": 0.7516855597496033,
+      "learning_rate": 0.0002406299489706141,
+      "loss": 3.304,
+      "step": 3375
+    },
+    {
+      "epoch": 0.6158718986450818,
+      "grad_norm": 0.7859501242637634,
+      "learning_rate": 0.0002384304064754531,
+      "loss": 3.2958,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6158718986450818,
+      "eval_loss": 2.7763619422912598,
+      "eval_runtime": 91.3446,
+      "eval_samples_per_second": 107.833,
+      "eval_steps_per_second": 4.149,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6378673235966918,
+      "grad_norm": 0.754370927810669,
+      "learning_rate": 0.00023623086398029207,
+      "loss": 3.2671,
+      "step": 3625
+    },
+    {
+      "epoch": 0.659862748548302,
+      "grad_norm": 0.8835521936416626,
+      "learning_rate": 0.00023403132148513107,
+      "loss": 3.284,
+      "step": 3750
+    },
+    {
+      "epoch": 0.6818581734999121,
+      "grad_norm": 0.7852393984794617,
+      "learning_rate": 0.00023183177898997007,
+      "loss": 3.2879,
+      "step": 3875
+    },
+    {
+      "epoch": 0.7038535984515221,
+      "grad_norm": 0.6869296431541443,
+      "learning_rate": 0.00022963223649480905,
+      "loss": 3.2702,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7038535984515221,
+      "eval_loss": 2.7806477546691895,
+      "eval_runtime": 91.4522,
+      "eval_samples_per_second": 107.707,
+      "eval_steps_per_second": 4.144,
+      "step": 4000
     }
   ],
   "logging_steps": 125,
@@ -243,7 +315,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1760138625024000.0,
+  "total_flos": 2346851500032000.0,
   "train_batch_size": 26,
   "trial_name": null,
   "trial_params": null