Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
     "up_proj",
     "q_proj",
-    "gate_proj",
-    "down_proj",
-    "k_proj",
-    "v_proj"
+    "o_proj",
+    "gate_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 sha256:1dda52f7280a623558f2f1badc8eed1542227c2d3acba34c3a828aa856ac54e6
+oid sha256:e7651809d59ce9fddd038896ce9a6262e9e974e0ce4863ebfecac41a6098e05d
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25356f1d4da875880fb13346a4087d097ad469aced44a354bf5582f0c250ed7
+oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7092244c60798e1ab03d4fe68ee97ba243124819620dca59a1f7c2ad2682481a
+oid sha256:fcecbcc564666edf6af81b027426d9673e892a66966056d8334ef5d45a66687e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008137689709891361,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00016275379419782723,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 0.00016275379419782723,
       "eval_loss": NaN,
-      "eval_runtime": 98.0752,
-      "eval_samples_per_second": 26.388,
-      "eval_steps_per_second": 13.194,
+      "eval_runtime": 98.8948,
+      "eval_samples_per_second": 26.169,
+      "eval_steps_per_second": 13.085,
       "step": 1
-    },
-    {
-      "epoch": 0.0008137689709891362,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.0016275379419782724,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.0016275379419782724,
-      "eval_loss": NaN,
-      "eval_runtime": 96.1277,
-      "eval_samples_per_second": 26.923,
-      "eval_steps_per_second": 13.461,
-      "step": 10
-    },
-    {
-      "epoch": 0.0024413069129674086,
-      "grad_norm": NaN,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.0,
-      "step": 15
-    },
-    {
-      "epoch": 0.0032550758839565447,
-      "grad_norm": NaN,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.0032550758839565447,
-      "eval_loss": NaN,
-      "eval_runtime": 96.3166,
-      "eval_samples_per_second": 26.87,
-      "eval_steps_per_second": 13.435,
-      "step": 20
-    },
-    {
-      "epoch": 0.0040688448549456805,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.004882613825934817,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.004882613825934817,
-      "eval_loss": NaN,
-      "eval_runtime": 96.1049,
-      "eval_samples_per_second": 26.929,
-      "eval_steps_per_second": 13.464,
-      "step": 30
-    },
-    {
-      "epoch": 0.005696382796923953,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.0065101517679130895,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.0065101517679130895,
-      "eval_loss": NaN,
-      "eval_runtime": 97.204,
-      "eval_samples_per_second": 26.624,
-      "eval_steps_per_second": 13.312,
-      "step": 40
-    },
-    {
-      "epoch": 0.007323920738902225,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.008137689709891361,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.008137689709891361,
-      "eval_loss": NaN,
-      "eval_runtime": 96.3324,
-      "eval_samples_per_second": 26.865,
-      "eval_steps_per_second": 13.433,
-      "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1621491292569600.0,
+  "total_flos": 32429825851392.0,
   "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:df76a4c05bbc42d99540dd30b072867e13b8f0c30519021509fc13cfbd89b419
+oid sha256:45f9b5fcf840d6972221ecf3dfe5dc817d4e8ee106916ec3ab15c03d839149dc
 size 6776