Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "v_proj",
     "up_proj",
-    "gate_proj",
     "o_proj",
-    "v_proj",
     "k_proj",
+    "gate_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02abea1a5c33a35ba69b4b69c42d98a4bf19dccfc3d64a4bdfd0f26acde25335
+oid sha256:b26bf10018ff56cb7e9391efdb3f48de33dd2b930939c1ecef3f9692a2793acd
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c006909030ae0cd3bccf29886b677d0dbbb09d64edc3e94708fe8187b2c23f3a
+oid sha256:56ec46c409c764e9b3a1db69dd58aa841a3d41cbac4340e0a1f8da11dac027f7
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f3dd2d0a091a302e7d561fe8532f63a666092f6556b354ddb5bdb93e236096
+oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
 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": 0.007417022065640645,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0001483404413128129,
+  "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": 0.0001483404413128129,
       "eval_loss": 5.5551042556762695,
-      "eval_runtime": 136.7872,
-      "eval_samples_per_second": 20.755,
-      "eval_steps_per_second": 10.381,
+      "eval_runtime": 139.0971,
+      "eval_samples_per_second": 20.41,
+      "eval_steps_per_second": 10.209,
       "step": 1
-    },
-    {
-      "epoch": 0.0007417022065640646,
-      "grad_norm": 2.9662487506866455,
-      "learning_rate": 5e-05,
-      "loss": 5.1492,
-      "step": 5
-    },
-    {
-      "epoch": 0.0014834044131281292,
-      "grad_norm": 2.82889461517334,
-      "learning_rate": 0.0001,
-      "loss": 5.0396,
-      "step": 10
-    },
-    {
-      "epoch": 0.0014834044131281292,
-      "eval_loss": 4.797138690948486,
-      "eval_runtime": 136.1155,
-      "eval_samples_per_second": 20.857,
-      "eval_steps_per_second": 10.432,
-      "step": 10
-    },
-    {
-      "epoch": 0.0022251066196921935,
-      "grad_norm": 2.4060170650482178,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 4.224,
-      "step": 15
-    },
-    {
-      "epoch": 0.0029668088262562583,
-      "grad_norm": 2.7258360385894775,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 3.9751,
-      "step": 20
-    },
-    {
-      "epoch": 0.0029668088262562583,
-      "eval_loss": 3.643627882003784,
-      "eval_runtime": 136.7907,
-      "eval_samples_per_second": 20.754,
-      "eval_steps_per_second": 10.381,
-      "step": 20
-    },
-    {
-      "epoch": 0.0037085110328203227,
-      "grad_norm": 3.8353631496429443,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 3.5626,
-      "step": 25
-    },
-    {
-      "epoch": 0.004450213239384387,
-      "grad_norm": 1.9700348377227783,
-      "learning_rate": 5e-05,
-      "loss": 3.3118,
-      "step": 30
-    },
-    {
-      "epoch": 0.004450213239384387,
-      "eval_loss": 3.42592716217041,
-      "eval_runtime": 136.4101,
-      "eval_samples_per_second": 20.812,
-      "eval_steps_per_second": 10.41,
-      "step": 30
-    },
-    {
-      "epoch": 0.005191915445948452,
-      "grad_norm": 2.3600919246673584,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 3.487,
-      "step": 35
-    },
-    {
-      "epoch": 0.005933617652512517,
-      "grad_norm": 2.286428451538086,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 3.0723,
-      "step": 40
-    },
-    {
-      "epoch": 0.005933617652512517,
-      "eval_loss": 3.357463836669922,
-      "eval_runtime": 139.4856,
-      "eval_samples_per_second": 20.353,
-      "eval_steps_per_second": 10.18,
-      "step": 40
-    },
-    {
-      "epoch": 0.006675319859076581,
-      "grad_norm": 2.1259288787841797,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 3.3444,
-      "step": 45
-    },
-    {
-      "epoch": 0.007417022065640645,
-      "grad_norm": 2.0974245071411133,
-      "learning_rate": 0.0,
-      "loss": 3.2276,
-      "step": 50
-    },
-    {
-      "epoch": 0.007417022065640645,
-      "eval_loss": 3.3513498306274414,
-      "eval_runtime": 138.1093,
-      "eval_samples_per_second": 20.556,
-      "eval_steps_per_second": 10.282,
-      "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": 3428033180467200.0,
+  "total_flos": 68560663609344.0,
   "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:ec282507b5882fd0aa83d0a49ad2fb9d1c2ff11e894e2877b06a7e7ed83b6be9
+oid sha256:1c0a09cd6dc53ce1b959efc512ea8880ffff90cc92ecc0c51bf48493a23af55b
 size 6776