Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
-    "down_proj",
-    "gate_proj",
     "o_proj",
-    "q_proj",
-    "k_proj"
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_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 sha256:330f480ca85d54d8aec7921b54cd4c1571ab6d27836a9b0e5266374b486368f3
+oid sha256:8d6774c2f3e9f6f2132a4c7df8c004a7c78dbb0cc88a1bb84fa017267ba66638
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087a1090196cda7889e8f861db5faa376b19e6e3c7602e5893f2f4a05308740b
+oid sha256:4ae659f6062603ef01f9041f43bb6b82ee9690bac22d36fee8736c0e506096c6
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6438ca723a6279488973c611dac02868446fef8d2c6b1ca3b67dfd2dba930c99
+oid sha256:4795d4ea56c7bbad5211d2c89fae5345ee850d3d5c0e1e07519d9a59aa43f322
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedb4b16013794621ec166dcdb46a864e9da3b8d28d3167c3185decf0aa836d9
+oid sha256:cdcaa7acd195c38164b4cfbf58785ff6734ceab7758dfdb61896569eab8b07e5
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e6b004d66732b5c7788323760ddb7b26ee1b3e268f331cfc1e0a6658096ae3
+oid sha256:baa69e4ebb63bfeb4e88c45801fdb42750a3fa6277fe4f9fe4d56ed19c32d86b
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5c9fa3b6189f77fcb760c349fe8b8b98776fa13b429a7d38ff2dad08ec00c8
+oid sha256:5c92eb97aacc162626fcb37b2a08d27a4a6c62b113bfc34d97fe5ad2f725325d
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9f3cefb26a955da44b4238b76355ee8565d71ff5ae0a60fb4b2b3d370e2026
+oid sha256:fcc1f4d4a90d2a47485c2a01cffea2c7d0aa965cc37c7bc4811695e15285c17c
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9792cd18e45820071f5f38e8efdcc24155c2102e3d2cc6152b4f1b665b0a1e1
+oid sha256:6218d3540a34000a8339db820d471f0c6f72898d0cff5ecf14b16071095f7ada
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0f3fbe785bb4e3bf6b64e082e8cbb5bd3865b6500110f49b733ebbebcb4091
+oid sha256:848af25dd310dd5e992dbdcc38b72c78ef73ba9fb01fdb9bdd954d67598d92cd
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9addb03aee9449e54a662d9667088607fd2c5559698385c03261d3545672e823
+oid sha256:960b66ac8b1d130aa6b93ee5269727c03e2b6a2b28c32a2440608aaf0bf6fd20
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014134275618374558,
+  "epoch": 0.028268551236749116,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0028268551236749115,
       "eval_loss": 7.129258632659912,
-      "eval_runtime": 20.9973,
-      "eval_samples_per_second": 28.385,
-      "eval_steps_per_second": 3.572,
+      "eval_runtime": 13.6697,
+      "eval_samples_per_second": 43.6,
+      "eval_steps_per_second": 5.487,
       "step": 1
     },
     {
@@ -32,14 +32,14 @@
     },
     {
       "epoch": 0.008480565371024734,
-      "grad_norm": 5.082520484924316,
+      "grad_norm": 5.114774703979492,
       "learning_rate": 2e-05,
       "loss": 7.4669,
       "step": 3
     },
     {
       "epoch": 0.011307420494699646,
-      "grad_norm": 4.920047760009766,
+      "grad_norm": 4.991275310516357,
       "learning_rate": 4e-05,
       "loss": 7.1521,
       "step": 4
@@ -48,16 +48,59 @@
       "epoch": 0.014134275618374558,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 7.7426,
+      "loss": 7.7429,
       "step": 5
     },
     {
       "epoch": 0.014134275618374558,
-      "eval_loss": 7.097348213195801,
-      "eval_runtime": 20.8903,
-      "eval_samples_per_second": 28.53,
-      "eval_steps_per_second": 3.59,
+      "eval_loss": 7.097643852233887,
+      "eval_runtime": 20.7137,
+      "eval_samples_per_second": 28.773,
+      "eval_steps_per_second": 3.621,
       "step": 5
+    },
+    {
+      "epoch": 0.01696113074204947,
+      "grad_norm": 4.559197902679443,
+      "learning_rate": 6e-05,
+      "loss": 7.1861,
+      "step": 6
+    },
+    {
+      "epoch": 0.019787985865724382,
+      "grad_norm": 3.6284019947052,
+      "learning_rate": 8e-05,
+      "loss": 6.9673,
+      "step": 7
+    },
+    {
+      "epoch": 0.022614840989399292,
+      "grad_norm": 4.3491082191467285,
+      "learning_rate": 0.0001,
+      "loss": 7.2919,
+      "step": 8
+    },
+    {
+      "epoch": 0.025441696113074206,
+      "grad_norm": 3.08682918548584,
+      "learning_rate": 0.00012,
+      "loss": 7.258,
+      "step": 9
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "grad_norm": 3.268092393875122,
+      "learning_rate": 0.00014,
+      "loss": 7.0434,
+      "step": 10
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "eval_loss": 6.333721160888672,
+      "eval_runtime": 20.9199,
+      "eval_samples_per_second": 28.49,
+      "eval_steps_per_second": 3.585,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6719419828928512.0,
+  "total_flos": 1.3204441146589184e+16,
   "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 sha256:0b55d7424e01d2da7c827809f0e75e814ca3307809331f5d1880db7934ea6a65
+oid sha256:676c5b957839737d77485c6332fc96de69385066f3eef0d74b47f677462f11dc
 size 6712