Training in progress, step 310, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0cf25f76e8662756856fd1a097be6ff3870d9f310686bf41f15fe00f6e14dc4
+oid sha256:80811b878fbdd5efdd4f08e7b0bd3a4c9633c207c497739ecac63cd5a9eca669
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742095389fc358571b77e198008ebd180a04e2384f21dd14cc648803058e1cfe
+oid sha256:e73ae7c4dc344be3442d36391cb4ba52cfd5d97e4bb25bc22948ccdfd1f87bdf
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e1effb06033458f08c521267ddbc73b4a5a3e148e528b2cfd2ce1d0d17a805
+oid sha256:876d99865a3847c750dc39ca4a3b8622be8f667a3f24db9221e48742faf0c0fe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2e7670b3561000eee216684d0727bea9800d1c3f3b2422105732155595c43d
+oid sha256:68293b71e7e6e68b301413d0698f3727535763528fb8f34f0fe9f273150e3e61
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.26369168356998,
+  "epoch": 2.5152129817444218,
   "eval_steps": 31,
-  "global_step": 279,
+  "global_step": 310,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -738,6 +738,84 @@
       "eval_samples_per_second": 15.481,
       "eval_steps_per_second": 1.935,
       "step": 279
+    },
+    {
+      "epoch": 2.288032454361055,
+      "grad_norm": 5.454842567443848,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0822,
+      "step": 282
+    },
+    {
+      "epoch": 2.31237322515213,
+      "grad_norm": 5.592954635620117,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.9626,
+      "step": 285
+    },
+    {
+      "epoch": 2.336713995943205,
+      "grad_norm": 5.249399662017822,
+      "learning_rate": 1.22645209888614e-05,
+      "loss": 0.8161,
+      "step": 288
+    },
+    {
+      "epoch": 2.36105476673428,
+      "grad_norm": 5.653781890869141,
+      "learning_rate": 1.1418770830614013e-05,
+      "loss": 0.9639,
+      "step": 291
+    },
+    {
+      "epoch": 2.385395537525355,
+      "grad_norm": 5.4389119148254395,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.868,
+      "step": 294
+    },
+    {
+      "epoch": 2.40973630831643,
+      "grad_norm": 5.680983543395996,
+      "learning_rate": 9.807156969139136e-06,
+      "loss": 1.1558,
+      "step": 297
+    },
+    {
+      "epoch": 2.4340770791075053,
+      "grad_norm": 8.884838104248047,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.9113,
+      "step": 300
+    },
+    {
+      "epoch": 2.4584178498985803,
+      "grad_norm": 6.362790107727051,
+      "learning_rate": 8.305708896641594e-06,
+      "loss": 1.0533,
+      "step": 303
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 6.722659111022949,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.945,
+      "step": 306
+    },
+    {
+      "epoch": 2.5070993914807302,
+      "grad_norm": 4.19068717956543,
+      "learning_rate": 6.918541977923709e-06,
+      "loss": 0.8369,
+      "step": 309
+    },
+    {
+      "epoch": 2.5152129817444218,
+      "eval_loss": 0.5427043437957764,
+      "eval_runtime": 13.4361,
+      "eval_samples_per_second": 15.481,
+      "eval_steps_per_second": 1.935,
+      "step": 310
     }
   ],
   "logging_steps": 3,
@@ -757,7 +835,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.706262291176489e+17,
+  "total_flos": 4.118715981197476e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null