Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "up_proj",
+    "o_proj",
     "q_proj",
-    "k_proj",
     "down_proj",
-    "up_proj",
-    "v_proj",
-    "o_proj"
+    "k_proj",
+    "v_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:b0304deb94d880a7178e25c4a9e95080cad45ede8dec464157f33bd332f16447
+oid sha256:096d0d1306c228ce8c01652e2e9dc22fbfdf66e56fe1c3cc3c3f3341baa59e44
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a811aacff4dbcf4c4e10cb5d8bb1badbc2b48eebd1d3c4546998b6c6da9bb1cf
+oid sha256:43253be831e7ac99582443feb4b0497d91e5b08f1a4d38fec8bab185fced7dca
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2343ae5ff828c34e3305a42016ad344256fbf938ac207504145e5fbdf0daff67
+oid sha256:e1d0df08df7fd9b105c27325b0d737ee5dbb265a2a2aac9c9bc9fa9f7953db2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02702702702702703,
+  "epoch": 0.008108108108108109,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.002702702702702703,
-      "grad_norm": 0.22516648471355438,
+      "grad_norm": 0.2378644198179245,
       "learning_rate": 2e-05,
       "loss": 2.4235,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.002702702702702703,
       "eval_loss": 2.200819492340088,
-      "eval_runtime": 8.0954,
-      "eval_samples_per_second": 9.635,
-      "eval_steps_per_second": 9.635,
+      "eval_runtime": 23.968,
+      "eval_samples_per_second": 3.254,
+      "eval_steps_per_second": 3.254,
       "step": 1
     },
     {
       "epoch": 0.005405405405405406,
-      "grad_norm": 0.2626628577709198,
+      "grad_norm": 0.2817547917366028,
       "learning_rate": 4e-05,
       "loss": 2.2166,
       "step": 2
     },
     {
       "epoch": 0.008108108108108109,
-      "grad_norm": 0.21446576714515686,
+      "grad_norm": 0.22646959125995636,
       "learning_rate": 6e-05,
-      "loss": 2.6546,
+      "loss": 2.6545,
       "step": 3
     },
     {
       "epoch": 0.008108108108108109,
-      "eval_loss": 2.199615955352783,
-      "eval_runtime": 8.2871,
-      "eval_samples_per_second": 9.412,
-      "eval_steps_per_second": 9.412,
+      "eval_loss": 2.1994752883911133,
+      "eval_runtime": 23.8826,
+      "eval_samples_per_second": 3.266,
+      "eval_steps_per_second": 3.266,
       "step": 3
-    },
-    {
-      "epoch": 0.010810810810810811,
-      "grad_norm": 0.2510293424129486,
-      "learning_rate": 8e-05,
-      "loss": 2.6251,
-      "step": 4
-    },
-    {
-      "epoch": 0.013513513513513514,
-      "grad_norm": 0.2600695788860321,
-      "learning_rate": 0.0001,
-      "loss": 2.0934,
-      "step": 5
-    },
-    {
-      "epoch": 0.016216216216216217,
-      "grad_norm": 0.23503589630126953,
-      "learning_rate": 0.00012,
-      "loss": 2.3495,
-      "step": 6
-    },
-    {
-      "epoch": 0.016216216216216217,
-      "eval_loss": 2.193514585494995,
-      "eval_runtime": 8.4696,
-      "eval_samples_per_second": 9.209,
-      "eval_steps_per_second": 9.209,
-      "step": 6
-    },
-    {
-      "epoch": 0.01891891891891892,
-      "grad_norm": 0.23834799230098724,
-      "learning_rate": 0.00014,
-      "loss": 2.0365,
-      "step": 7
-    },
-    {
-      "epoch": 0.021621621621621623,
-      "grad_norm": 0.34777796268463135,
-      "learning_rate": 0.00016,
-      "loss": 2.0777,
-      "step": 8
-    },
-    {
-      "epoch": 0.024324324324324326,
-      "grad_norm": 0.2863074839115143,
-      "learning_rate": 0.00018,
-      "loss": 2.3295,
-      "step": 9
-    },
-    {
-      "epoch": 0.024324324324324326,
-      "eval_loss": 2.1840600967407227,
-      "eval_runtime": 8.339,
-      "eval_samples_per_second": 9.354,
-      "eval_steps_per_second": 9.354,
-      "step": 9
-    },
-    {
-      "epoch": 0.02702702702702703,
-      "grad_norm": 0.25496789813041687,
-      "learning_rate": 0.0002,
-      "loss": 2.1022,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3467932965273600.0,
+  "total_flos": 1017260336480256.0,
   "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:d5b80978b6cdcc9339ecc7931db757328a1ca9deca5507d6af70e88c187855a9
+oid sha256:fd961290b5c1511222dcde7c5274eeb95e8e3143dbf3b403d7a4f50c5202a8b5
 size 6776