Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "q_proj",
+    "k_proj",
     "v_proj",
     "up_proj",
-    "down_proj",
-    "k_proj"
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "down_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 sha256:220f097d60c1bbe8d4e19bc1a4242c1ea0c314b5d808ef96a0182294400f796c
+oid sha256:1fd90cd092dd528c9b4615ba812a24900a79f4e4a0f6b5c8ea5166affab65391
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7745f45d31f6de3b531d94a50470c61a7f609d77f9911f401c48d05088df9f0f
+oid sha256:1cbe2a9850d0ec25d10e55aa299060508e8b615eb57c2571581e2defc218f73c
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
+oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03537944454272068,
+  "epoch": 0.009198655581107376,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,120 +11,32 @@
     {
       "epoch": 0.0007075888908544136,
       "eval_loss": 10.552796363830566,
-      "eval_runtime": 47.6033,
-      "eval_samples_per_second": 12.499,
-      "eval_steps_per_second": 6.26,
+      "eval_runtime": 98.5911,
+      "eval_samples_per_second": 6.035,
+      "eval_steps_per_second": 3.023,
       "step": 1
     },
     {
       "epoch": 0.0035379444542720678,
-      "grad_norm": 27.365083694458008,
+      "grad_norm": 25.988548278808594,
       "learning_rate": 5e-05,
-      "loss": 10.6636,
+      "loss": 10.6611,
       "step": 5
     },
     {
       "epoch": 0.0070758889085441356,
-      "grad_norm": 26.378427505493164,
+      "grad_norm": 26.148916244506836,
       "learning_rate": 0.0001,
-      "loss": 7.7571,
+      "loss": 7.6885,
       "step": 10
     },
     {
       "epoch": 0.0070758889085441356,
-      "eval_loss": 4.241506099700928,
-      "eval_runtime": 47.9132,
-      "eval_samples_per_second": 12.418,
-      "eval_steps_per_second": 6.22,
+      "eval_loss": 4.3447370529174805,
+      "eval_runtime": 99.5463,
+      "eval_samples_per_second": 5.977,
+      "eval_steps_per_second": 2.994,
       "step": 10
-    },
-    {
-      "epoch": 0.010613833362816204,
-      "grad_norm": 27.92503547668457,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 2.7767,
-      "step": 15
-    },
-    {
-      "epoch": 0.014151777817088271,
-      "grad_norm": 6.907174110412598,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.4931,
-      "step": 20
-    },
-    {
-      "epoch": 0.014151777817088271,
-      "eval_loss": 0.3619968593120575,
-      "eval_runtime": 47.9815,
-      "eval_samples_per_second": 12.401,
-      "eval_steps_per_second": 6.211,
-      "step": 20
-    },
-    {
-      "epoch": 0.01768972227136034,
-      "grad_norm": 6.215694904327393,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.3552,
-      "step": 25
-    },
-    {
-      "epoch": 0.021227666725632408,
-      "grad_norm": 9.718087196350098,
-      "learning_rate": 5e-05,
-      "loss": 0.2788,
-      "step": 30
-    },
-    {
-      "epoch": 0.021227666725632408,
-      "eval_loss": 0.191437229514122,
-      "eval_runtime": 48.0246,
-      "eval_samples_per_second": 12.389,
-      "eval_steps_per_second": 6.205,
-      "step": 30
-    },
-    {
-      "epoch": 0.024765611179904477,
-      "grad_norm": 2.682128667831421,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.2684,
-      "step": 35
-    },
-    {
-      "epoch": 0.028303555634176542,
-      "grad_norm": 7.8806047439575195,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.1783,
-      "step": 40
-    },
-    {
-      "epoch": 0.028303555634176542,
-      "eval_loss": 0.14547115564346313,
-      "eval_runtime": 48.0415,
-      "eval_samples_per_second": 12.385,
-      "eval_steps_per_second": 6.203,
-      "step": 40
-    },
-    {
-      "epoch": 0.03184150008844861,
-      "grad_norm": 6.912134647369385,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.1846,
-      "step": 45
-    },
-    {
-      "epoch": 0.03537944454272068,
-      "grad_norm": 8.270027160644531,
-      "learning_rate": 0.0,
-      "loss": 0.3082,
-      "step": 50
-    },
-    {
-      "epoch": 0.03537944454272068,
-      "eval_loss": 0.1359296292066574,
-      "eval_runtime": 47.9346,
-      "eval_samples_per_second": 12.413,
-      "eval_steps_per_second": 6.217,
-      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -139,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 9555457081344000.0,
+  "total_flos": 2484418841149440.0,
   "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:f8a1c27b701f34958ad813edda152841a969d7b236718f385b16c51625ffc35b
+oid sha256:840510acd1178540e7455c69d6218492e95457c020739adb7f5684c8133a873c
 size 6776