Training in progress, step 48, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "v_proj",
     "q_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
     "down_proj",
-    "o_proj",
-    "k_proj"
+    "o_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 sha256:85c8e3f6e4686a9eaf26d4d35a5b42dc0c000d9b6f962ccd1b8794f560d5f89c
+oid sha256:e37e61238b135747fcc3d40a6da7df9fcaf155660d8bdc93dcdfb98cb955210f
 size 240145026

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de5d1d932a2179cf22c7901338ddf8e09617563006e9d5fcd9e53d14a97bd90
+oid sha256:b1457a5693acbfd430e65eb4f240dc952d7f6c81b743b04ad01829ee7a0e4dea
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa9b82845f4f5cb4b96438388210115365f9fbf9335c646df7c795feec61941
+oid sha256:2a96825c30763d5ab1c72bbaeb82e2bacd35db8260f49dc8a317321f7fd5a0bb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c42292d086c5053372eb94b916df672dbae0f4c4eba1b19f26fd0411f6bd958
+oid sha256:8de2d7f9ade22f9813a1c13ba5b10587377d9b25e1449d3219450bcdb6025268
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7a347273f6ea9aada39cb7d7b4a9a36c2c3704435d52b399f6fc29ca67d828
+oid sha256:0c93ce2986ee4dd2437366340dd639953a12ca4dc41f3178e7769b255f8b1337
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814b79b47e12bde76b22a1ac4fd2f1e7ddf84c332d0b19c3538a1fad1c6cc96e
+oid sha256:ba6fd801ed573bc507b53e922ba337a0ba782f238e16ef13f7ef24143336ab21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6126482213438735,
+  "epoch": 3.130434782608696,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.06324110671936758,
       "eval_loss": NaN,
-      "eval_runtime": 1.9758,
-      "eval_samples_per_second": 54.155,
-      "eval_steps_per_second": 7.086,
+      "eval_runtime": 1.0459,
+      "eval_samples_per_second": 102.3,
+      "eval_steps_per_second": 13.385,
       "step": 1
     },
     {
@@ -194,10 +194,171 @@
     {
       "epoch": 1.6126482213438735,
       "eval_loss": NaN,
-      "eval_runtime": 1.9567,
-      "eval_samples_per_second": 54.685,
-      "eval_steps_per_second": 7.155,
+      "eval_runtime": 1.043,
+      "eval_samples_per_second": 102.584,
+      "eval_steps_per_second": 13.422,
       "step": 25
+    },
+    {
+      "epoch": 1.6758893280632412,
+      "grad_norm": NaN,
+      "learning_rate": 4.658787933176646e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": NaN,
+      "learning_rate": 4.319166754518768e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8023715415019763,
+      "grad_norm": NaN,
+      "learning_rate": 3.982719934736832e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.8656126482213438,
+      "grad_norm": NaN,
+      "learning_rate": 3.651016144214878e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.9288537549407114,
+      "grad_norm": NaN,
+      "learning_rate": 3.325601939145069e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.0237154150197627,
+      "grad_norm": NaN,
+      "learning_rate": 3.007994550768793e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "grad_norm": NaN,
+      "learning_rate": 2.6996748113442394e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.150197628458498,
+      "grad_norm": NaN,
+      "learning_rate": 2.4020802498228335e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.2134387351778657,
+      "grad_norm": NaN,
+      "learning_rate": 2.1165983894256647e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.2766798418972334,
+      "grad_norm": NaN,
+      "learning_rate": 1.8445602783697374e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.3399209486166006,
+      "grad_norm": NaN,
+      "learning_rate": 1.5872342839067306e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.4031620553359683,
+      "grad_norm": NaN,
+      "learning_rate": 1.3458201786093794e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.466403162055336,
+      "grad_norm": NaN,
+      "learning_rate": 1.1214435464779006e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.5296442687747036,
+      "grad_norm": NaN,
+      "learning_rate": 9.151505349477902e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.5928853754940713,
+      "grad_norm": NaN,
+      "learning_rate": 7.2790297726755716e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.6561264822134385,
+      "grad_norm": NaN,
+      "learning_rate": 5.605739079881239e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.719367588932806,
+      "grad_norm": NaN,
+      "learning_rate": 4.139434924727359e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": NaN,
+      "learning_rate": 2.88695389405898e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.8458498023715415,
+      "grad_norm": NaN,
+      "learning_rate": 1.8541356326100433e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": NaN,
+      "learning_rate": 1.0457956158838544e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 3.0039525691699605,
+      "grad_norm": NaN,
+      "learning_rate": 4.6570269818346224e-07,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 3.067193675889328,
+      "grad_norm": NaN,
+      "learning_rate": 1.1656154047303691e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 3.130434782608696,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -221,12 +382,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.1506187337728e+16,
+  "total_flos": 9.889187968843776e+16,
   "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 sha256:028c826a2bc9d200c1c305c5204cb3f86600ee25223d25cf379b917f3408363e
+oid sha256:24bf98ed40615884a8a6303e66dd174db02ee7fa16a60a5e1f3908c763d298c5
 size 6776