Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "gate_proj",
-    "q_proj",
-    "v_proj",
+    "up_proj",
     "down_proj",
     "o_proj",
-    "up_proj"
+    "k_proj",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf92819c598c0f176d87f4df9c4e0c28e10ceafdf2b928e48456d66e8c369ee
+oid sha256:75562e3246a15d26b7654f8abe42110e9bb645beea72e7da02ed584dd6d51aa0
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b458dd6844e0edb003f819901a5972d01ad3b409cdd0ec81c9085fb30c55ce2
+oid sha256:af887195d9102f95a0b4678d3f9fa8ab999068b984520645fd8728fe7a4cf6f9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1ec64e7fb6599268675ffae336ab0bffa16d474229806515cc6de572654114
+oid sha256:7e852727044612131607769e3e4333c7d479fd14397bc37763b029ec244be27c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694f97946598c42a19de3a84642296c5c6077e8c33d25cd2a055db7a4d01e8b5
+oid sha256:d060097f81f47d8a41114eb43684500adefb0e0e6e04d04b458e491d841f71c7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6e81d2a11731db8799b547cb8ed1920ed621ddefcfa2978e3314f72aa0e16a
+oid sha256:f6acbd6461870f37978517ad2f9b02c805098d3ca2d81571740355e276f11228
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
+oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05751258087706686,
+  "epoch": 0.02875629043853343,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0011502516175413372,
       "eval_loss": NaN,
-      "eval_runtime": 3.0856,
-      "eval_samples_per_second": 16.205,
-      "eval_steps_per_second": 4.213,
+      "eval_runtime": 3.0824,
+      "eval_samples_per_second": 16.221,
+      "eval_steps_per_second": 4.217,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.02875629043853343,
       "eval_loss": NaN,
-      "eval_runtime": 3.1283,
-      "eval_samples_per_second": 15.983,
-      "eval_steps_per_second": 4.156,
+      "eval_runtime": 3.1168,
+      "eval_samples_per_second": 16.042,
+      "eval_steps_per_second": 4.171,
       "step": 25
-    },
-    {
-      "epoch": 0.029906542056074768,
-      "grad_norm": NaN,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.031056793673616103,
-      "grad_norm": NaN,
-      "learning_rate": 5.205685918464356e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.03220704529115744,
-      "grad_norm": NaN,
-      "learning_rate": 4.912632135009769e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.03335729690869878,
-      "grad_norm": NaN,
-      "learning_rate": 4.6220935509274235e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.03450754852624011,
-      "grad_norm": NaN,
-      "learning_rate": 4.3353142970386564e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.035657800143781455,
-      "grad_norm": NaN,
-      "learning_rate": 4.053522406135775e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.03680805176132279,
-      "grad_norm": NaN,
-      "learning_rate": 3.777924554357096e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.037958303378864126,
-      "grad_norm": NaN,
-      "learning_rate": 3.509700894014496e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.03910855499640546,
-      "grad_norm": NaN,
-      "learning_rate": 3.250000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.040258806613946804,
-      "grad_norm": NaN,
-      "learning_rate": 2.9999339514117912e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.04140905823148814,
-      "grad_norm": NaN,
-      "learning_rate": 2.760573569460757e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.042559309849029475,
-      "grad_norm": NaN,
-      "learning_rate": 2.53294383204969e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.04370956146657081,
-      "grad_norm": NaN,
-      "learning_rate": 2.3180194846605367e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.044859813084112146,
-      "grad_norm": NaN,
-      "learning_rate": 2.1167208663446025e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.04601006470165349,
-      "grad_norm": NaN,
-      "learning_rate": 1.9299099686894423e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.047160316319194824,
-      "grad_norm": NaN,
-      "learning_rate": 1.758386744638546e-05,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.04831056793673616,
-      "grad_norm": NaN,
-      "learning_rate": 1.602885682970026e-05,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.049460819554277495,
-      "grad_norm": NaN,
-      "learning_rate": 1.464072663102903e-05,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.05061107117181884,
-      "grad_norm": NaN,
-      "learning_rate": 1.3425421036992098e-05,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.05176132278936017,
-      "grad_norm": NaN,
-      "learning_rate": 1.2388144172720251e-05,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.05291157440690151,
-      "grad_norm": NaN,
-      "learning_rate": 1.1533337816991932e-05,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.054061826024442844,
-      "grad_norm": NaN,
-      "learning_rate": 1.0864662381854632e-05,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.055212077641984186,
-      "grad_norm": NaN,
-      "learning_rate": 1.0384981238178534e-05,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.05636232925952552,
-      "grad_norm": NaN,
-      "learning_rate": 1.0096348454262845e-05,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.05751258087706686,
-      "grad_norm": NaN,
-      "learning_rate": 1e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.05751258087706686,
-      "eval_loss": NaN,
-      "eval_runtime": 3.1173,
-      "eval_samples_per_second": 16.039,
-      "eval_steps_per_second": 4.17,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -395,12 +212,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.658021338284032e+17,
+  "total_flos": 2.829010669142016e+17,
   "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 sha256:1b93a38ad8edd172ea3a9260afa9631b977c8642185a974202ac2e7d4dd15c40
+oid sha256:de98de8cc6ca3a9ae44682f3927b770958eec429e01439d80b4b96e1306f4b31
 size 6840