Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60661d2d2583d4765a71aa4fe25b1abf5edc35f7fe00c95c81e579fbaca57ea4
+oid sha256:35c3d917c3253743e3698a5a508a9d126be2f1e32bdc7dac1045cb54e8f984b5
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc928a9072ed0184329b633d0d8dd2da8b142a22fd534e7c8996f7482da017fa
-size 14960
+oid sha256:544666a42f191b8fe70a72850271c3b69fb40d0de2036c7d042ce7ff82120fc0
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b14ef23db20a9cc1ed6bbc267cf349df0d7752c7cd1979d1919067d5ad3569
+oid sha256:e59162a4fe141b7122a1530f69894ef9c019f1084d5d1a47601c10279312a2f2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc26e6f800d1ae46418856c0feb7b64c747dc416a02089e355aa7c3ba9bf3f56
+oid sha256:791c4f66c210bc642f024b4971c2872d7d472f45488e3401488b18a0fa57624d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d982e8e1d6792f92e0eb5e29d97004e5d8b85954626a89dfb2e6ae2a623cf57b
+oid sha256:104f27ad8d6aa1d4d088db8d2e8bfaa766a84fe10d417db5c6324a2ca9191677
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6230529595015576,
+  "epoch": 1.2461059190031152,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.024922118380062305,
       "eval_loss": NaN,
-      "eval_runtime": 5.6431,
-      "eval_samples_per_second": 47.846,
-      "eval_steps_per_second": 6.025,
+      "eval_runtime": 2.9609,
+      "eval_samples_per_second": 91.188,
+      "eval_steps_per_second": 11.483,
       "step": 1
     },
     {
@@ -194,10 +194,193 @@
     {
       "epoch": 0.6230529595015576,
       "eval_loss": NaN,
-      "eval_runtime": 5.5286,
-      "eval_samples_per_second": 48.837,
-      "eval_steps_per_second": 6.15,
+      "eval_runtime": 2.9586,
+      "eval_samples_per_second": 91.258,
+      "eval_steps_per_second": 11.492,
       "step": 25
+    },
+    {
+      "epoch": 0.6479750778816199,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.6728971962616822,
+      "grad_norm": NaN,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.6978193146417445,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.7227414330218068,
+      "grad_norm": NaN,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.7725856697819314,
+      "grad_norm": NaN,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.7975077881619937,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.822429906542056,
+      "grad_norm": NaN,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.8473520249221184,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.8722741433021807,
+      "grad_norm": NaN,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.9221183800623053,
+      "grad_norm": NaN,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.9470404984423676,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.9719626168224299,
+      "grad_norm": NaN,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.0218068535825544,
+      "grad_norm": NaN,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.0467289719626167,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.071651090342679,
+      "grad_norm": NaN,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.0965732087227413,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.1214953271028036,
+      "grad_norm": NaN,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.146417445482866,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.1713395638629283,
+      "grad_norm": NaN,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.1962616822429906,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 1.2211838006230529,
+      "grad_norm": NaN,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 1.2461059190031152,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.2461059190031152,
+      "eval_loss": NaN,
+      "eval_runtime": 2.9586,
+      "eval_samples_per_second": 91.261,
+      "eval_steps_per_second": 11.492,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372431cf5d215cc9cbc0915c2e3f7c9cedcc04697ee854b92077999ee82a49b4
+oid sha256:edd401ba4d208defa37ed0be15448a68e421311b62d4639e8f6482bbc4f0d047
 size 6776