Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "q_proj",
     "o_proj",
-    "k_proj",
     "gate_proj",
-    "up_proj",
     "down_proj",
-    "v_proj"
+    "v_proj",
+    "k_proj",
+    "up_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 sha256:62f863207b9110340a4345fefd7f48d86abdd8f1d77c805d7651656acf562dc4
+oid sha256:f585486ff20690a46b77eca03e32e70dc3373bca533999db3e69f43062e81540
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93eaadba5527a8f2bb162883da6b13e860086e91033212a3ee8fb061143f0d8e
+oid sha256:d0d408935c28046baae094a230cbd697d51fc78aa249ff0a4a8c73ea817962e1
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60def06e8d16b47623b67a4aae8194c19582b3e85d8800ca2e3bc17092d1bb5
+oid sha256:ce8441b6f44f4e2fa1d2c030527340ac0218aae059aebad5b78181cb84cf26fe
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbfd43de7fb2acc21f9de1871048cc58018d000e5907250651f158a613d62d3
+oid sha256:dc75c68691d11d10bcc57bd372463d3e0df9a0caca3bec2a2287a78f782bdcb7
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,107 +1,78 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003799472295514512,
+  "epoch": 0.005065428450823132,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.00042216358839050134,
+      "epoch": 0.0008442380751371887,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 6.2311,
+      "loss": 6.2949,
       "step": 1
     },
     {
-      "epoch": 0.00042216358839050134,
-      "eval_loss": 7.166989326477051,
-      "eval_runtime": 34.0119,
-      "eval_samples_per_second": 14.671,
-      "eval_steps_per_second": 14.671,
+      "epoch": 0.0008442380751371887,
+      "eval_loss": 7.167040824890137,
+      "eval_runtime": 33.9503,
+      "eval_samples_per_second": 14.698,
+      "eval_steps_per_second": 7.364,
       "step": 1
     },
     {
-      "epoch": 0.0008443271767810027,
-      "grad_norm": 5.0110015869140625,
-      "learning_rate": 2e-05,
-      "loss": 6.3049,
+      "epoch": 0.0016884761502743773,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 7.5932,
       "step": 2
     },
     {
-      "epoch": 0.001266490765171504,
-      "grad_norm": NaN,
+      "epoch": 0.002532714225411566,
+      "grad_norm": 4.345782279968262,
       "learning_rate": 2e-05,
-      "loss": 7.0367,
+      "loss": 6.3083,
       "step": 3
     },
     {
-      "epoch": 0.001266490765171504,
-      "eval_loss": 7.166989326477051,
-      "eval_runtime": 33.8177,
-      "eval_samples_per_second": 14.756,
-      "eval_steps_per_second": 14.756,
+      "epoch": 0.002532714225411566,
+      "eval_loss": 7.167040824890137,
+      "eval_runtime": 33.7762,
+      "eval_samples_per_second": 14.774,
+      "eval_steps_per_second": 7.402,
       "step": 3
     },
     {
-      "epoch": 0.0016886543535620053,
-      "grad_norm": 7.560422897338867,
+      "epoch": 0.0033769523005487546,
+      "grad_norm": 4.228282451629639,
       "learning_rate": 4e-05,
-      "loss": 7.5846,
+      "loss": 6.5425,
       "step": 4
     },
     {
-      "epoch": 0.0021108179419525065,
-      "grad_norm": 5.9173455238342285,
+      "epoch": 0.004221190375685944,
+      "grad_norm": 5.7301530838012695,
       "learning_rate": 6e-05,
-      "loss": 6.8106,
+      "loss": 7.4106,
       "step": 5
     },
     {
-      "epoch": 0.002532981530343008,
-      "grad_norm": 5.743566036224365,
+      "epoch": 0.005065428450823132,
+      "grad_norm": 4.481907367706299,
       "learning_rate": 8e-05,
-      "loss": 5.7917,
+      "loss": 6.8524,
       "step": 6
     },
     {
-      "epoch": 0.002532981530343008,
-      "eval_loss": 6.941962718963623,
-      "eval_runtime": 34.2264,
-      "eval_samples_per_second": 14.579,
-      "eval_steps_per_second": 14.579,
+      "epoch": 0.005065428450823132,
+      "eval_loss": 6.865447521209717,
+      "eval_runtime": 33.823,
+      "eval_samples_per_second": 14.753,
+      "eval_steps_per_second": 7.391,
       "step": 6
-    },
-    {
-      "epoch": 0.0029551451187335093,
-      "grad_norm": 5.3699951171875,
-      "learning_rate": 0.0001,
-      "loss": 6.6086,
-      "step": 7
-    },
-    {
-      "epoch": 0.0033773087071240107,
-      "grad_norm": 6.26664400100708,
-      "learning_rate": 0.00012,
-      "loss": 5.8944,
-      "step": 8
-    },
-    {
-      "epoch": 0.003799472295514512,
-      "grad_norm": 7.683081150054932,
-      "learning_rate": 0.00014,
-      "loss": 5.9806,
-      "step": 9
-    },
-    {
-      "epoch": 0.003799472295514512,
-      "eval_loss": 6.024622440338135,
-      "eval_runtime": 34.5272,
-      "eval_samples_per_second": 14.452,
-      "eval_steps_per_second": 14.452,
-      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -121,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1664607823331328.0,
+  "total_flos": 2219477097775104.0,
   "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:d8a0e1d575435a385945acb2379c55d79d6b7da826961709cf6ad2467a2bcd7a
+oid sha256:91b17704c84342df8c4881fcb5acc78d90d7b0fb6bb4b955a77926f3bd16d0fc
 size 6776