Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
+    "up_proj",
     "gate_proj",
     "k_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "up_proj"
+    "v_proj",
+    "o_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 sha256:466b11276018812b5c59b678a7398a7319bdb7c1e30acf1661de3592ef0dd6be
+oid sha256:19930f5003696feeb8b9478f1bc2a8e5799f0fd874f16c46c8959edeafe14592
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5474917045503e225f9c7639301f8f3a2ecfd2d8b710d7a66fb6f9398354c9d
+oid sha256:74ad98f16de29161ac68f04ee51c4247953656f046ff971fb8bd040e25cbd018
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a6e54f9735ac650e1bce7d31fe07be9de05d82d7f44a83bbaaeae992231fe8
+oid sha256:20911ca91ea1cdbb81acbe54f05a1245788489144f858e8e56a7eb8a4d073e18
 size 14244

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03230148048452221,
+  "epoch": 0.016150740242261104,
   "eval_steps": 3,
   "global_step": 6,
   "is_hyper_param_search": false,
@@ -9,69 +9,69 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.005383580080753701,
-      "grad_norm": 1.332345962524414,
+      "epoch": 0.0026917900403768506,
+      "grad_norm": 1.408136248588562,
       "learning_rate": 2e-05,
-      "loss": 0.7345,
+      "loss": 0.7399,
       "step": 1
     },
     {
-      "epoch": 0.005383580080753701,
-      "eval_loss": 0.7382340431213379,
-      "eval_runtime": 7.7076,
-      "eval_samples_per_second": 10.25,
-      "eval_steps_per_second": 5.19,
+      "epoch": 0.0026917900403768506,
+      "eval_loss": 0.7382442355155945,
+      "eval_runtime": 6.3386,
+      "eval_samples_per_second": 12.463,
+      "eval_steps_per_second": 12.463,
       "step": 1
     },
     {
-      "epoch": 0.010767160161507403,
-      "grad_norm": 1.5144602060317993,
+      "epoch": 0.005383580080753701,
+      "grad_norm": 1.402262568473816,
       "learning_rate": 4e-05,
-      "loss": 0.7732,
+      "loss": 0.7274,
       "step": 2
     },
     {
-      "epoch": 0.016150740242261104,
-      "grad_norm": 1.4010770320892334,
+      "epoch": 0.008075370121130552,
+      "grad_norm": 1.6652259826660156,
       "learning_rate": 6e-05,
-      "loss": 0.7996,
+      "loss": 0.7714,
       "step": 3
     },
     {
-      "epoch": 0.016150740242261104,
-      "eval_loss": 0.6860002279281616,
-      "eval_runtime": 7.8686,
-      "eval_samples_per_second": 10.04,
-      "eval_steps_per_second": 5.083,
+      "epoch": 0.008075370121130552,
+      "eval_loss": 0.6933578848838806,
+      "eval_runtime": 6.3351,
+      "eval_samples_per_second": 12.47,
+      "eval_steps_per_second": 12.47,
       "step": 3
     },
     {
-      "epoch": 0.021534320323014805,
-      "grad_norm": 1.2587902545928955,
+      "epoch": 0.010767160161507403,
+      "grad_norm": 1.429751992225647,
       "learning_rate": 8e-05,
-      "loss": 0.665,
+      "loss": 0.7393,
       "step": 4
     },
     {
-      "epoch": 0.026917900403768506,
-      "grad_norm": 1.1400635242462158,
+      "epoch": 0.013458950201884253,
+      "grad_norm": 1.4376033544540405,
       "learning_rate": 0.0001,
-      "loss": 0.6649,
+      "loss": 0.7399,
       "step": 5
     },
     {
-      "epoch": 0.03230148048452221,
-      "grad_norm": 0.9094105362892151,
+      "epoch": 0.016150740242261104,
+      "grad_norm": 1.3412057161331177,
       "learning_rate": 0.00012,
-      "loss": 0.5525,
+      "loss": 0.6919,
       "step": 6
     },
     {
-      "epoch": 0.03230148048452221,
-      "eval_loss": 0.5270073413848877,
-      "eval_runtime": 7.7898,
-      "eval_samples_per_second": 10.141,
-      "eval_steps_per_second": 5.135,
+      "epoch": 0.016150740242261104,
+      "eval_loss": 0.5569691061973572,
+      "eval_runtime": 6.5483,
+      "eval_samples_per_second": 12.064,
+      "eval_steps_per_second": 12.064,
       "step": 6
     }
   ],
@@ -92,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2774346405773312.0,
+  "total_flos": 1387173186109440.0,
   "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 sha256:9a212cd389246f94d793758aff17e074e70be0b5a2ee39d33914356f9a22c4aa
+oid sha256:add0e59b79de04b92c19a082f4b4bd8afdd3721024dd528eee811fafb0ec960e
 size 6776