Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
+    "q_proj",
+    "o_proj",
     "down_proj",
+    "gate_proj",
     "v_proj",
-    "up_proj",
-    "o_proj",
-    "gate_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:c5af6ceb3181bdf7e95868525dbe4d63abbe2473764de299720779b4cbec0c86
+oid sha256:da65eabaff7444caebfca33a37a9f8c43cd8d44d08a32899b2ea4fe748ab1eb4
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f47ddd4884e6a4f3bac407a7bb5c7f96019f61a010b4c239e1d97e79684b9c
+oid sha256:58127ec95c47906630700b67ebefd82002b7f15d052f046d10bd905bba926c37
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b066a8111fb29f260f02e04781565f7c6f077dac9e7e2f1f2830addf102652f8
+oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006896551724137931,
+  "epoch": 0.013793103448275862,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0022988505747126436,
       "eval_loss": NaN,
-      "eval_runtime": 55.532,
-      "eval_samples_per_second": 3.313,
-      "eval_steps_per_second": 1.657,
+      "eval_runtime": 42.2453,
+      "eval_samples_per_second": 4.356,
+      "eval_steps_per_second": 2.178,
       "step": 1
     },
     {
@@ -40,10 +40,39 @@
     {
       "epoch": 0.006896551724137931,
       "eval_loss": NaN,
-      "eval_runtime": 54.6552,
-      "eval_samples_per_second": 3.367,
-      "eval_steps_per_second": 1.683,
+      "eval_runtime": 55.0777,
+      "eval_samples_per_second": 3.341,
+      "eval_steps_per_second": 1.67,
       "step": 3
+    },
+    {
+      "epoch": 0.009195402298850575,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.013793103448275862,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.013793103448275862,
+      "eval_loss": NaN,
+      "eval_runtime": 54.6418,
+      "eval_samples_per_second": 3.367,
+      "eval_steps_per_second": 1.684,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 216286290247680.0,
+  "total_flos": 432572580495360.0,
   "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 sha256:1f6b294cad946c00780426710004bacbf6fd30dfe8b06f26312ddc12c2facb93
+oid sha256:d591a82bd15320e6a861c112681dce84191047c1aa2c6eed1c86e87e1a090555
 size 6776