Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "down_proj",
-    "o_proj",
     "up_proj",
+    "o_proj",
+    "k_proj",
     "gate_proj",
-    "k_proj"
+    "q_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 sha256:4c8cfac24ff0d3e238a815b333f2ea43cf11b4d6fea1fd7ae85e5916aa356a26
+oid sha256:63a202a643f27c5a084a406e3d9fcdadeed3e307d936d87819bd3e33fa72afda
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbdaa7f8ee336181c7adfc9dfa44e8b569a2588db424e11cfebb72b6592e69b
+oid sha256:4a549a30c15a77b0e4d2167218887a9c36e3703902f43ffab17c9832b9e95e29
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
+oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0029942360955161314,
+  "epoch": 0.002694812485964518,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0002994236095516131,
       "eval_loss": 11.5775728225708,
-      "eval_runtime": 95.8713,
-      "eval_samples_per_second": 7.343,
-      "eval_steps_per_second": 7.343,
+      "eval_runtime": 95.8227,
+      "eval_samples_per_second": 7.347,
+      "eval_steps_per_second": 7.347,
       "step": 1
     },
     {
@@ -40,75 +40,68 @@
     {
       "epoch": 0.0008982708286548395,
       "eval_loss": 11.5775728225708,
-      "eval_runtime": 94.6943,
-      "eval_samples_per_second": 7.434,
-      "eval_steps_per_second": 7.434,
+      "eval_runtime": 95.0865,
+      "eval_samples_per_second": 7.404,
+      "eval_steps_per_second": 7.404,
       "step": 3
     },
     {
       "epoch": 0.0011976944382064525,
-      "grad_norm": 11.335941314697266,
+      "grad_norm": 10.02202320098877,
       "learning_rate": 2e-05,
       "loss": 9.5838,
       "step": 4
     },
     {
       "epoch": 0.0014971180477580657,
-      "grad_norm": 12.509073257446289,
+      "grad_norm": 11.54944896697998,
       "learning_rate": 4e-05,
       "loss": 11.0567,
       "step": 5
     },
     {
       "epoch": 0.001796541657309679,
-      "grad_norm": 13.569826126098633,
+      "grad_norm": 12.557976722717285,
       "learning_rate": 6e-05,
-      "loss": 12.2136,
+      "loss": 12.2132,
       "step": 6
     },
     {
       "epoch": 0.001796541657309679,
-      "eval_loss": 11.521071434020996,
-      "eval_runtime": 94.7717,
-      "eval_samples_per_second": 7.428,
-      "eval_steps_per_second": 7.428,
+      "eval_loss": 11.523130416870117,
+      "eval_runtime": 94.7466,
+      "eval_samples_per_second": 7.43,
+      "eval_steps_per_second": 7.43,
       "step": 6
     },
     {
       "epoch": 0.002095965266861292,
-      "grad_norm": 12.041800498962402,
+      "grad_norm": 10.816157341003418,
       "learning_rate": 8e-05,
-      "loss": 11.451,
+      "loss": 11.453,
       "step": 7
     },
     {
       "epoch": 0.002395388876412905,
-      "grad_norm": 12.907513618469238,
+      "grad_norm": 11.840999603271484,
       "learning_rate": 0.0001,
-      "loss": 11.1969,
+      "loss": 11.202,
       "step": 8
     },
     {
       "epoch": 0.002694812485964518,
-      "grad_norm": 8.735396385192871,
+      "grad_norm": 8.202712059020996,
       "learning_rate": 0.00012,
-      "loss": 9.0545,
+      "loss": 9.0586,
       "step": 9
     },
     {
       "epoch": 0.002694812485964518,
-      "eval_loss": 11.052964210510254,
-      "eval_runtime": 95.5747,
-      "eval_samples_per_second": 7.366,
-      "eval_steps_per_second": 7.366,
+      "eval_loss": 11.066697120666504,
+      "eval_runtime": 95.5362,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 7.369,
       "step": 9
-    },
-    {
-      "epoch": 0.0029942360955161314,
-      "grad_norm": 7.92449951171875,
-      "learning_rate": 0.00014,
-      "loss": 10.0,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +116,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 1,
   "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:ed5cf1a7f24b2f4b6ffdd137a7076d460d56660645e71b5af0068e2d73030f31
+oid sha256:1ee223a43027b8c8afd21622e4578463f433159b96d4ac348cc6f399af5db597
 size 6776