Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "gate_proj",
-    "v_proj",
-    "q_proj",
     "down_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
+    "gate_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da1e5df6dd46517be3b326f62976396c589661c34fd28648c58dd75d02d8ed6b
+oid sha256:fcfa77e704a64d02fdec392b40a94fb48db317e3c900b1268708b49c323dded4
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc6fc6da86591f0b7156cfc2da8f98c3e4e05ad25a783d5c0396ee830002084
+oid sha256:728eec445470e6c3556074d04c3eb74a9573a71fcf7daaa88e905e2fb2d2578e
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
+oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.376173973133422e-05,
+  "epoch": 0.00012564260959700132,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 1.396028995522237e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1878.2928,
-      "eval_samples_per_second": 8.029,
-      "eval_steps_per_second": 8.029,
+      "eval_runtime": 1842.0549,
+      "eval_samples_per_second": 8.187,
+      "eval_steps_per_second": 8.187,
       "step": 1
     },
     {
@@ -40,14 +40,14 @@
     {
       "epoch": 4.188086986566711e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1814.1651,
-      "eval_samples_per_second": 8.313,
-      "eval_steps_per_second": 8.313,
+      "eval_runtime": 1823.007,
+      "eval_samples_per_second": 8.273,
+      "eval_steps_per_second": 8.273,
       "step": 3
     },
     {
       "epoch": 5.584115982088948e-05,
-      "grad_norm": 0.47626373171806335,
+      "grad_norm": 0.45489802956581116,
       "learning_rate": 2e-05,
       "loss": 1.6525,
       "step": 4
@@ -61,18 +61,47 @@
     },
     {
       "epoch": 8.376173973133422e-05,
-      "grad_norm": 0.632369339466095,
+      "grad_norm": 0.6043833494186401,
       "learning_rate": 4e-05,
       "loss": 1.5735,
       "step": 6
     },
     {
       "epoch": 8.376173973133422e-05,
-      "eval_loss": 1.8685113191604614,
-      "eval_runtime": 1813.0543,
-      "eval_samples_per_second": 8.318,
-      "eval_steps_per_second": 8.318,
+      "eval_loss": 1.8686633110046387,
+      "eval_runtime": 1822.7895,
+      "eval_samples_per_second": 8.274,
+      "eval_steps_per_second": 8.274,
       "step": 6
+    },
+    {
+      "epoch": 9.77220296865566e-05,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 1.7572,
+      "step": 7
+    },
+    {
+      "epoch": 0.00011168231964177897,
+      "grad_norm": 0.5930614471435547,
+      "learning_rate": 6e-05,
+      "loss": 1.8795,
+      "step": 8
+    },
+    {
+      "epoch": 0.00012564260959700132,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 1.6314,
+      "step": 9
+    },
+    {
+      "epoch": 0.00012564260959700132,
+      "eval_loss": 1.862870216369629,
+      "eval_runtime": 1821.1166,
+      "eval_samples_per_second": 8.281,
+      "eval_steps_per_second": 8.281,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 977239881547776.0,
+  "total_flos": 1465859822321664.0,
   "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 sha256:8592505319a0e1bd652dbec69d0ae190ac2673d977246a6c07d54713cd9bce43
+oid sha256:41e2120fce261a3f11caf9498f0f2c7c47b2d4840984af1e8cfb44d3982cfeb2
 size 6776