Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "up_proj",
     "gate_proj",
+    "v_proj",
     "k_proj",
-    "up_proj",
-    "down_proj",
     "q_proj",
+    "down_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8c3f21ac0274f31126ab156bf1bf105e6f1a3ebf53cbf8431e0ff2f37014ba
+oid sha256:3293a8a1eb1d98f95ae6a8e8eb8951ff87094792bb9a7203c4c68eb0e1b7fa27
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9a0e2e05d9eacf5c069bd04337e5de4a41461f12fee894e25c6f74e61bcfb7
+oid sha256:d8cdd28be9549af1d5bae665c6e126d72e4da1f2ba57ad65c7b14a6a4a333524
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3871a6dd003957f74dd719d49313b586008e765ed00522a4df1d6a65f799a8
+oid sha256:200e6fcd481c16b4f3d1cbb24a0867b14067141b424637d8e0b176938ed6cbb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009989594172736733,
+  "epoch": 0.00149843912591051,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.00016649323621227888,
       "eval_loss": NaN,
-      "eval_runtime": 543.5334,
-      "eval_samples_per_second": 4.653,
-      "eval_steps_per_second": 2.327,
+      "eval_runtime": 541.5183,
+      "eval_samples_per_second": 4.67,
+      "eval_steps_per_second": 2.336,
       "step": 1
     },
     {
@@ -40,9 +40,9 @@
     {
       "epoch": 0.0004994797086368366,
       "eval_loss": NaN,
-      "eval_runtime": 540.7666,
-      "eval_samples_per_second": 4.677,
-      "eval_steps_per_second": 2.339,
+      "eval_runtime": 540.5845,
+      "eval_samples_per_second": 4.678,
+      "eval_steps_per_second": 2.34,
       "step": 3
     },
     {
@@ -69,10 +69,39 @@
     {
       "epoch": 0.0009989594172736733,
       "eval_loss": NaN,
-      "eval_runtime": 541.4238,
-      "eval_samples_per_second": 4.671,
-      "eval_steps_per_second": 2.336,
+      "eval_runtime": 540.514,
+      "eval_samples_per_second": 4.679,
+      "eval_steps_per_second": 2.34,
       "step": 6
+    },
+    {
+      "epoch": 0.0011654526534859522,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.001331945889698231,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00149843912591051,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00149843912591051,
+      "eval_loss": NaN,
+      "eval_runtime": 540.6919,
+      "eval_samples_per_second": 4.677,
+      "eval_steps_per_second": 2.34,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1567522604187648.0,
+  "total_flos": 2351283906281472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a25691fb6a6b3d2d3ebf285b08a1fc54e133279caff6a277ec551d3b09b830
+oid sha256:edd5c8003dc212a5d55ed2476be46f188433095a148c73d1f0610fae7d6df834
 size 6776