Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "up_proj",
     "gate_proj",
     "k_proj",
-    "q_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21101be3f2578dea61017dec401770c9d94090e8c532e49059856959e61f6b55
+oid sha256:71d28ff05b039bc1ae7a8f446118fa45d60a537104c6bc9266b01df44275a78d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e2baddaf1d69caca788f2f3a96826392458aa83f7fe994f7bd4067df65817f
+oid sha256:148db3067c9e11932f52a06d284cdfc30862d0a461ea6dda19d701e1f9680f4d
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b846f8d2a10084120751b041296c0c0c3eb9165ba7cc8bbbfae022d208689d86
+oid sha256:507e4c02e3b5f657804d730431a12039cc97d6fab264b4f08cc14b81749131af
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427ca1b5388c4924bd841729a462ad57d6a324024690a8fdb036c0af2438c76e
+oid sha256:275c9b344b4d9dfa4dc9bcd94265d40f00021e5205289d412cf5ee562cc92731
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026917900403768506,
+  "epoch": 0.05383580080753701,
   "eval_steps": 3,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -9,105 +9,105 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0026917900403768506,
-      "grad_norm": 1.408136248588562,
+      "epoch": 0.005383580080753701,
+      "grad_norm": 1.332345962524414,
       "learning_rate": 2e-05,
-      "loss": 0.7399,
+      "loss": 0.7345,
       "step": 1
     },
     {
-      "epoch": 0.0026917900403768506,
-      "eval_loss": 0.7382442355155945,
-      "eval_runtime": 6.3386,
-      "eval_samples_per_second": 12.463,
-      "eval_steps_per_second": 12.463,
+      "epoch": 0.005383580080753701,
+      "eval_loss": 0.7382340431213379,
+      "eval_runtime": 7.7076,
+      "eval_samples_per_second": 10.25,
+      "eval_steps_per_second": 5.19,
       "step": 1
     },
     {
-      "epoch": 0.005383580080753701,
-      "grad_norm": 1.402262568473816,
+      "epoch": 0.010767160161507403,
+      "grad_norm": 1.5144602060317993,
       "learning_rate": 4e-05,
-      "loss": 0.7274,
+      "loss": 0.7732,
       "step": 2
     },
     {
-      "epoch": 0.008075370121130552,
-      "grad_norm": 1.6652259826660156,
+      "epoch": 0.016150740242261104,
+      "grad_norm": 1.4010770320892334,
       "learning_rate": 6e-05,
-      "loss": 0.7714,
+      "loss": 0.7996,
       "step": 3
     },
     {
-      "epoch": 0.008075370121130552,
-      "eval_loss": 0.6933578848838806,
-      "eval_runtime": 6.3351,
-      "eval_samples_per_second": 12.47,
-      "eval_steps_per_second": 12.47,
+      "epoch": 0.016150740242261104,
+      "eval_loss": 0.6860002279281616,
+      "eval_runtime": 7.8686,
+      "eval_samples_per_second": 10.04,
+      "eval_steps_per_second": 5.083,
       "step": 3
     },
     {
-      "epoch": 0.010767160161507403,
-      "grad_norm": 1.429751992225647,
+      "epoch": 0.021534320323014805,
+      "grad_norm": 1.2587902545928955,
       "learning_rate": 8e-05,
-      "loss": 0.7393,
+      "loss": 0.665,
       "step": 4
     },
     {
-      "epoch": 0.013458950201884253,
-      "grad_norm": 1.4376033544540405,
+      "epoch": 0.026917900403768506,
+      "grad_norm": 1.1400635242462158,
       "learning_rate": 0.0001,
-      "loss": 0.7399,
+      "loss": 0.6649,
       "step": 5
     },
     {
-      "epoch": 0.016150740242261104,
-      "grad_norm": 1.3412057161331177,
+      "epoch": 0.03230148048452221,
+      "grad_norm": 0.9094105362892151,
       "learning_rate": 0.00012,
-      "loss": 0.6919,
+      "loss": 0.5525,
       "step": 6
     },
     {
-      "epoch": 0.016150740242261104,
-      "eval_loss": 0.5569691061973572,
-      "eval_runtime": 6.5483,
-      "eval_samples_per_second": 12.064,
-      "eval_steps_per_second": 12.064,
+      "epoch": 0.03230148048452221,
+      "eval_loss": 0.5270073413848877,
+      "eval_runtime": 7.7898,
+      "eval_samples_per_second": 10.141,
+      "eval_steps_per_second": 5.135,
       "step": 6
     },
     {
-      "epoch": 0.018842530282637954,
-      "grad_norm": 1.139148473739624,
-      "learning_rate": 0.00014,
-      "loss": 0.4971,
+      "epoch": 0.03768506056527591,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.5412,
       "step": 7
     },
     {
-      "epoch": 0.021534320323014805,
-      "grad_norm": 1.1586865186691284,
-      "learning_rate": 0.00016,
-      "loss": 0.4434,
+      "epoch": 0.04306864064602961,
+      "grad_norm": 0.9600444436073303,
+      "learning_rate": 0.00014,
+      "loss": 0.6705,
       "step": 8
     },
     {
-      "epoch": 0.024226110363391656,
-      "grad_norm": 1.3152556419372559,
-      "learning_rate": 0.00018,
-      "loss": 0.4553,
+      "epoch": 0.04845222072678331,
+      "grad_norm": 1.114023208618164,
+      "learning_rate": 0.00016,
+      "loss": 0.4857,
       "step": 9
     },
     {
-      "epoch": 0.024226110363391656,
-      "eval_loss": 0.4071764349937439,
-      "eval_runtime": 6.4684,
-      "eval_samples_per_second": 12.213,
-      "eval_steps_per_second": 12.213,
+      "epoch": 0.04845222072678331,
+      "eval_loss": 0.424485981464386,
+      "eval_runtime": 7.7991,
+      "eval_samples_per_second": 10.129,
+      "eval_steps_per_second": 5.129,
       "step": 9
     },
     {
-      "epoch": 0.026917900403768506,
-      "grad_norm": 1.2165873050689697,
-      "learning_rate": 0.0002,
-      "loss": 0.4257,
+      "epoch": 0.05383580080753701,
+      "grad_norm": 0.8380860686302185,
+      "learning_rate": 0.00018,
+      "loss": 0.383,
       "step": 10
     }
   ],
@@ -128,7 +128,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2358194416386048.0,
+  "total_flos": 4716388916658176.0,
   "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:add0e59b79de04b92c19a082f4b4bd8afdd3721024dd528eee811fafb0ec960e
+oid sha256:9a212cd389246f94d793758aff17e074e70be0b5a2ee39d33914356f9a22c4aa
 size 6776