Training in progress, step 16700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa435505cd53f72a810061ae0179d098c329f5cd5a93585597b00b60e2b0852
+oid sha256:327275103777ce51a6d5e09152b86c71226274a0549f9f81c58051e619b5aa94
 size 161533160

last-checkpoint/adapter_config.json

@@ -25,12 +25,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj",
     "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
     "k_proj",
-    "down_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa435505cd53f72a810061ae0179d098c329f5cd5a93585597b00b60e2b0852
+oid sha256:f91e3c5f21cf129551bcf7c69bf4d8d16a4ef7f114f3eb09634873a47bacc359
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6e1601f052a39fe52b8e67d0f41d674600b2273f240f49e617d5a3508ba282
+oid sha256:4014d31deb4cce624d0816b7ea019aa4bc828b0109dcbd09f7797bdcac508304
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6916ff48b2e02e3d29ae3dfd2bd04494c3e738d0397d2c6aaa89fba13f73ad3d
+oid sha256:6863575074205cdae5bd9a3add89cf69a3951c4f077fb3f56f28f0fe9457c14f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.748344370860927,
+  "epoch": 2.7152317880794703,
   "eval_steps": 100,
-  "global_step": 16600,
+  "global_step": 16400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2336,34 +2336,6 @@
       "learning_rate": 2.7228170036058153e-06,
       "loss": 0.2617,
       "step": 16400
-    },
-    {
-      "epoch": 2.7235099337748343,
-      "grad_norm": 1.3112074136734009,
-      "learning_rate": 2.5682530093579626e-06,
-      "loss": 0.2751,
-      "step": 16450
-    },
-    {
-      "epoch": 2.7317880794701987,
-      "grad_norm": 1.3641598224639893,
-      "learning_rate": 2.418089536248769e-06,
-      "loss": 0.2741,
-      "step": 16500
-    },
-    {
-      "epoch": 2.7400662251655628,
-      "grad_norm": 1.2237251996994019,
-      "learning_rate": 2.2723405158236455e-06,
-      "loss": 0.2772,
-      "step": 16550
-    },
-    {
-      "epoch": 2.748344370860927,
-      "grad_norm": 1.171391248703003,
-      "learning_rate": 2.1310194700733697e-06,
-      "loss": 0.2715,
-      "step": 16600
     }
   ],
   "logging_steps": 50,
@@ -2383,7 +2355,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3026890823814349e+17,
+  "total_flos": 1.2874605314388787e+17,
   "train_batch_size": 1,
   "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:e16cd32295896d2f57f1f19dbc49310a6ac6c29a2ec738cf4fb0c11d34db588b
+oid sha256:4e7fd7045b4a15373c4d905f915edbb1436664635b44fe1df1bfa95de5188043
 size 5752

trainer_log.jsonl

@@ -2,3 +2,5 @@
 {"current_steps": 16500, "total_steps": 18120, "loss": 0.2741, "lr": 2.418089536248769e-06, "epoch": 2.7317880794701987, "percentage": 91.06, "elapsed_time": "0:10:04", "remaining_time": "0:00:59"}
 {"current_steps": 16550, "total_steps": 18120, "loss": 0.2772, "lr": 2.2723405158236455e-06, "epoch": 2.7400662251655628, "percentage": 91.34, "elapsed_time": "0:15:23", "remaining_time": "0:01:27"}
 {"current_steps": 16600, "total_steps": 18120, "loss": 0.2715, "lr": 2.1310194700733697e-06, "epoch": 2.748344370860927, "percentage": 91.61, "elapsed_time": "0:20:25", "remaining_time": "0:01:52"}
+{"current_steps": 16650, "total_steps": 18120, "loss": 0.2712, "lr": 1.9941395101795655e-06, "epoch": 2.756622516556291, "percentage": 91.89, "elapsed_time": "0:25:52", "remaining_time": "0:02:17"}
+{"current_steps": 16700, "total_steps": 18120, "loss": 0.2758, "lr": 1.861713335298282e-06, "epoch": 2.7649006622516556, "percentage": 92.16, "elapsed_time": "0:31:10", "remaining_time": "0:02:39"}