Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
     "q_proj",
+    "o_proj",
+    "gate_proj",
     "down_proj",
     "k_proj",
-    "gate_proj",
+    "v_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cee4030c1b570e5857557e24ae184f53e4a3ad0196a18c37d6a7cc2faac24fa
+oid sha256:738e47d9648b71fc9f5590df5b5cce84d80def88478768d46d6eaef7188e3f3e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb840ca5b557bbffad2cc222b43e043d509b9367102e4e676b630719c0c8f458
+oid sha256:153278cd63faea3747f4dfcd31bbfab667fd53c34f6b5ade45af8465ee28c8d4
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.75,
+  "epoch": 0.5,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,90 +18,61 @@
     {
       "epoch": 0.08333333333333333,
       "eval_loss": 1.4977792501449585,
-      "eval_runtime": 0.453,
-      "eval_samples_per_second": 6.622,
-      "eval_steps_per_second": 6.622,
+      "eval_runtime": 0.2209,
+      "eval_samples_per_second": 13.579,
+      "eval_steps_per_second": 13.579,
       "step": 1
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 4.665465831756592,
+      "grad_norm": 4.962691783905029,
       "learning_rate": 2e-05,
       "loss": 1.307,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 5.513491153717041,
+      "grad_norm": 5.919677734375,
       "learning_rate": 4e-05,
       "loss": 1.5735,
       "step": 3
     },
     {
       "epoch": 0.25,
-      "eval_loss": 1.4473786354064941,
-      "eval_runtime": 0.4679,
-      "eval_samples_per_second": 6.412,
-      "eval_steps_per_second": 6.412,
+      "eval_loss": 1.4450377225875854,
+      "eval_runtime": 0.2257,
+      "eval_samples_per_second": 13.291,
+      "eval_steps_per_second": 13.291,
       "step": 3
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 4.566956520080566,
+      "grad_norm": 4.771228313446045,
       "learning_rate": 6e-05,
-      "loss": 1.282,
+      "loss": 1.2789,
       "step": 4
     },
     {
       "epoch": 0.4166666666666667,
-      "grad_norm": 3.311328649520874,
+      "grad_norm": 3.510233163833618,
       "learning_rate": 8e-05,
-      "loss": 1.3071,
+      "loss": 1.3015,
       "step": 5
     },
     {
       "epoch": 0.5,
-      "grad_norm": 2.798964262008667,
+      "grad_norm": 2.8811535835266113,
       "learning_rate": 0.0001,
-      "loss": 1.0892,
+      "loss": 1.0788,
       "step": 6
     },
     {
       "epoch": 0.5,
-      "eval_loss": 0.8217151761054993,
-      "eval_runtime": 0.4475,
-      "eval_samples_per_second": 6.705,
-      "eval_steps_per_second": 6.705,
+      "eval_loss": 0.8092367053031921,
+      "eval_runtime": 0.2418,
+      "eval_samples_per_second": 12.405,
+      "eval_steps_per_second": 12.405,
       "step": 6
-    },
-    {
-      "epoch": 0.5833333333333334,
-      "grad_norm": 2.373387575149536,
-      "learning_rate": 0.00012,
-      "loss": 0.8337,
-      "step": 7
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 2.598729133605957,
-      "learning_rate": 0.00014,
-      "loss": 0.5417,
-      "step": 8
-    },
-    {
-      "epoch": 0.75,
-      "grad_norm": 2.8108651638031006,
-      "learning_rate": 0.00016,
-      "loss": 0.2385,
-      "step": 9
-    },
-    {
-      "epoch": 0.75,
-      "eval_loss": 0.05185846984386444,
-      "eval_runtime": 0.4321,
-      "eval_samples_per_second": 6.943,
-      "eval_steps_per_second": 6.943,
-      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -121,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1664607823331328.0,
+  "total_flos": 1109738548887552.0,
   "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:ab37ef2135f6555964c7f23e135ed3a58c3b21e0a8dfdabb28e1c2f6cc491bb9
+oid sha256:33ee77f9946e0ddfbac6f0c8ae58cf2871b3fdcb3ea1247868cf8374e044a7bd
 size 6776