Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f989b8a8a48cf9ae7f8d9c22cc7de38b07820f97627e46e6c647de8b8436fc3a
+oid sha256:39217b06d26794e7c43e9e0ad520f73221b1f8e2dd3d882f168d15442d48c879
 size 1073863208

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8f990f2bc7ec9116fc7df04ed0bc4f1c8658ef12d319dae17d00f0b241172d
+oid sha256:2b80d57176446efc8cc81628f82bca7d170fd1013c4e5dc8d4460f956999a2e9
 size 287329942

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b5691046896d865f067a1958689168fc2411c74d2f82d596bd6a636b2b141b
+oid sha256:9213080fe2b45399b87036ca9ff9164533abe6b368e5c828136ee184486749d4
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31d814c2a63b1f5c51675ff59fb7553fe12a663067f05c1719c12277701b430
+oid sha256:117a3bb552c8c6fe27c7588afd68ab718054d28dc5e3f6a1d52464601d26649e
 size 2080

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7692307692307692,
+  "epoch": 3.4615384615384617,
   "eval_steps": 3,
-  "global_step": 12,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,6 +183,170 @@
       "memory/max_mem_active(gib)": 34.71,
       "memory/max_mem_allocated(gib)": 34.71,
       "step": 12
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.08033885806798935,
+      "learning_rate": 0.00022500001068692654,
+      "loss": 2.0108,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 13
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.10752119868993759,
+      "learning_rate": 0.00020941196999046952,
+      "loss": 1.9729,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 14
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.08343259990215302,
+      "learning_rate": 0.0001930204889504239,
+      "loss": 1.9655,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 15
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "eval_loss": 2.0194833278656006,
+      "eval_runtime": 376.3527,
+      "eval_samples_per_second": 0.632,
+      "eval_steps_per_second": 0.316,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 15
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.08610356599092484,
+      "learning_rate": 0.00017604722233954817,
+      "loss": 1.9656,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 16
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.08564396947622299,
+      "learning_rate": 0.00015872172662056983,
+      "loss": 1.976,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 17
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.08958195149898529,
+      "learning_rate": 0.00014127828762866557,
+      "loss": 1.981,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 18
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "eval_loss": 2.014101505279541,
+      "eval_runtime": 376.448,
+      "eval_samples_per_second": 0.632,
+      "eval_steps_per_second": 0.316,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 18
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.10577207803726196,
+      "learning_rate": 0.000123952777357772,
+      "loss": 1.961,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 19
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.09847240895032883,
+      "learning_rate": 0.00010697951802285388,
+      "loss": 1.9455,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1634841412305832,
+      "learning_rate": 9.058803698280826e-05,
+      "loss": 1.9211,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 21
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.0099527835845947,
+      "eval_runtime": 376.3789,
+      "eval_samples_per_second": 0.632,
+      "eval_steps_per_second": 0.316,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 21
+    },
+    {
+      "epoch": 3.1538461538461537,
+      "grad_norm": 0.10216221213340759,
+      "learning_rate": 7.500000356230885e-05,
+      "loss": 1.9455,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 22
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "grad_norm": 0.11089015752077103,
+      "learning_rate": 6.042621680535376e-05,
+      "loss": 1.9001,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 23
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "grad_norm": 0.10617231577634811,
+      "learning_rate": 4.706375693785958e-05,
+      "loss": 1.9149,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 24
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "eval_loss": 2.009589910507202,
+      "eval_runtime": 376.3891,
+      "eval_samples_per_second": 0.632,
+      "eval_steps_per_second": 0.316,
+      "memory/device_mem_reserved(gib)": 38.55,
+      "memory/max_mem_active(gib)": 34.71,
+      "memory/max_mem_allocated(gib)": 34.71,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -202,7 +366,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4505824687122022e+17,
+  "total_flos": 2.829824816012329e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null