Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2df44592754fe7188dd677ae0bc32281f8bcfad5f4a6c037e3ae72d516e0f92
+oid sha256:6adbd6caf7bdf1842e91bc5816ccdd5448347927512e466c6ffec9628b45e389
 size 83946192

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4416518671bd3a5927dad1918e6feb19b8689187dec1647b573a84566f45c4
+oid sha256:cf81dd98ec9c616d55d1232f7ada73dc21309fa8c33dc3f10a7dbdc17291a944
 size 168150290

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b8115cb129c536e89826f236d6c4894075bda82a59ceefb56b1d1ccf0de0fb
+oid sha256:7ef525735c3cf9ca20902b64f335b1cb98298205e4df0c6e14b2c5e5e1d7d8dd
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167f19cbea1c5998444d9bc539623c9f6f524cce3680072969e6130b6d4da06a
+oid sha256:c6ff283720f8f76393837f434b89763e59f3450d2b659f4e3ad09ffbdff910d9
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4900141064667013,
+  "epoch": 0.5048630187838741,
   "eval_steps": 500,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4634,6 +4634,146 @@
       "learning_rate": 0.00012079116908177593,
       "loss": 0.9201,
       "step": 3300
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00012053755650651166,
+      "loss": 0.9375,
+      "step": 3305
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.337890625,
+      "learning_rate": 0.00012028380594270283,
+      "loss": 0.9681,
+      "step": 3310
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00012002991909525873,
+      "loss": 0.923,
+      "step": 3315
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00011977589767000433,
+      "loss": 0.9143,
+      "step": 3320
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00011952174337366881,
+      "loss": 0.9205,
+      "step": 3325
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00011926745791387406,
+      "loss": 0.9113,
+      "step": 3330
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00011901304299912326,
+      "loss": 0.9357,
+      "step": 3335
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00011875850033878939,
+      "loss": 0.9552,
+      "step": 3340
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00011850383164310371,
+      "loss": 0.9234,
+      "step": 3345
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00011824903862314427,
+      "loss": 0.9085,
+      "step": 3350
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.337890625,
+      "learning_rate": 0.00011799412299082448,
+      "loss": 0.9226,
+      "step": 3355
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00011773908645888152,
+      "loss": 0.9107,
+      "step": 3360
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00011748393074086497,
+      "loss": 0.9402,
+      "step": 3365
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00011722865755112504,
+      "loss": 0.9419,
+      "step": 3370
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00011697326860480133,
+      "loss": 0.9146,
+      "step": 3375
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.00011671776561781123,
+      "loss": 0.8996,
+      "step": 3380
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00011646215030683818,
+      "loss": 0.9089,
+      "step": 3385
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.0001162064243893205,
+      "loss": 0.9257,
+      "step": 3390
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00011595058958343952,
+      "loss": 0.924,
+      "step": 3395
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.00011569464760810825,
+      "loss": 0.9558,
+      "step": 3400
     }
   ],
   "logging_steps": 5,
@@ -4641,7 +4781,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 4.640654868195836e+18,
+  "total_flos": 4.781280773300814e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null