Training in progress, step 275, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c4947058fd8e7ee421b0b46fc349022d4a1f3f8246ef6c3d3b6bda09b72f50
+oid sha256:5d6c9e9fde3bf761964ce0a1096daf1a2f902a2ec3817c338700dd0fdb422b7b
 size 838904832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a651b2e845e714d6bbbfe26616bd79e994bd844b56c8ce9664fd66902226483
-size 420633876
+oid sha256:c44e3e00e2ab4d12e4e2b2418ce9291412c0dade8841637f3f38586085364aea
+size 421458386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1f20496eb68bf92a3c0bedec6630dbaf08516bee744709362b85a6b5810eb0
+oid sha256:5cecdcf6d8c7c779a0c31f47b4cfa05311ab6c9a135282cd57f3efb2ff76f57b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1650f5062195d8ee65b24ab00a137ab48cccbff41f41ba060d4208547a763c
+oid sha256:1cd2eafba86db0126a84de125a9a439f555cacfcb5b82fd7e6af07740e165b9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 1.1,
   "eval_steps": 500,
-  "global_step": 250,
+  "global_step": 275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1507,13 +1507,163 @@
       "learning_rate": 0.0002,
       "loss": 0.3503,
       "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 0.6092,
+      "step": 251
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002,
+      "loss": 0.5481,
+      "step": 252
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002,
+      "loss": 0.5902,
+      "step": 253
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 0.4603,
+      "step": 254
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 0.5344,
+      "step": 255
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 0.5136,
+      "step": 256
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.5304,
+      "step": 257
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.4625,
+      "step": 258
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002,
+      "loss": 0.4841,
+      "step": 259
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002,
+      "loss": 0.4548,
+      "step": 260
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002,
+      "loss": 0.4686,
+      "step": 261
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0002,
+      "loss": 0.4717,
+      "step": 262
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0002,
+      "loss": 0.4775,
+      "step": 263
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002,
+      "loss": 0.503,
+      "step": 264
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002,
+      "loss": 0.4712,
+      "step": 265
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002,
+      "loss": 0.4782,
+      "step": 266
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.4649,
+      "step": 267
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 268
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002,
+      "loss": 0.4192,
+      "step": 269
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002,
+      "loss": 0.4511,
+      "step": 270
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 271
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 0.4277,
+      "step": 272
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 0.4366,
+      "step": 273
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002,
+      "loss": 0.403,
+      "step": 274
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002,
+      "loss": 0.4161,
+      "step": 275
     }
   ],
   "logging_steps": 1,
-  "max_steps": 250,
-  "num_train_epochs": 1,
+  "max_steps": 500,
+  "num_train_epochs": 2,
   "save_steps": 25,
-  "total_flos": 2.990177006051328e+16,
+  "total_flos": 3.327201233842176e+16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ab7055ed2ab4ea386a14f2c54955245810bb73dc11cc1cce38f825dbf4c63e
+oid sha256:cf8ae64e171536bf78dc95ca36df03d7f40620336c1b55d8bd15bbd85cdd8bf5
 size 4600