Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3a59b8d07ffec409f080d114832aaadae842ee86092d982a9665e5cb7415fe
+oid sha256:a9e40d3e7c56cb46cd5a983275df9d038d806fdd848e034c4a041da2524b91e6
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ca34ab57cbc5b9c61f82581002e26b465a30bbf06b34c77ee426b13a0281df
+oid sha256:64cd5a60aa5e8bf4a4a45861316793a730820db2579d5d8c328fce981f9761b7
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883f28eb7c189cd34593e2e1d90c086421ac0e064f525f629bfedbc0ac7bb029
+oid sha256:e2580185eb0877da29c17fcb94b565a0adbb4fd61496abf5f574b0e4cc05bd14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8095238095238093,
+  "epoch": 0.47619047619047616,
   "eval_steps": 3,
-  "global_step": 30,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.09523809523809523,
-      "grad_norm": 0.5343478322029114,
+      "grad_norm": 0.5386500358581543,
       "learning_rate": 2e-05,
       "loss": 1.3356,
       "step": 1
@@ -18,293 +18,46 @@
     {
       "epoch": 0.09523809523809523,
       "eval_loss": 1.2671657800674438,
-      "eval_runtime": 20.0994,
-      "eval_samples_per_second": 4.975,
-      "eval_steps_per_second": 2.488,
+      "eval_runtime": 6.3713,
+      "eval_samples_per_second": 15.695,
+      "eval_steps_per_second": 7.848,
       "step": 1
     },
     {
       "epoch": 0.19047619047619047,
-      "grad_norm": 0.5495722889900208,
+      "grad_norm": 0.5549973845481873,
       "learning_rate": 4e-05,
       "loss": 1.3576,
       "step": 2
     },
     {
       "epoch": 0.2857142857142857,
-      "grad_norm": 0.48776495456695557,
+      "grad_norm": 0.4884030818939209,
       "learning_rate": 6e-05,
-      "loss": 1.2159,
+      "loss": 1.2158,
       "step": 3
     },
     {
       "epoch": 0.2857142857142857,
-      "eval_loss": 1.2533905506134033,
-      "eval_runtime": 24.7126,
-      "eval_samples_per_second": 4.047,
-      "eval_steps_per_second": 2.023,
+      "eval_loss": 1.2561376094818115,
+      "eval_runtime": 6.1155,
+      "eval_samples_per_second": 16.352,
+      "eval_steps_per_second": 8.176,
       "step": 3
     },
     {
       "epoch": 0.38095238095238093,
-      "grad_norm": 0.4593156576156616,
+      "grad_norm": 0.45884644985198975,
       "learning_rate": 8e-05,
-      "loss": 1.2203,
+      "loss": 1.2199,
       "step": 4
     },
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 0.3861481249332428,
+      "grad_norm": 0.3866402208805084,
       "learning_rate": 0.0001,
-      "loss": 1.278,
+      "loss": 1.2785,
       "step": 5
-    },
-    {
-      "epoch": 0.5714285714285714,
-      "grad_norm": 0.26556482911109924,
-      "learning_rate": 0.00012,
-      "loss": 1.2716,
-      "step": 6
-    },
-    {
-      "epoch": 0.5714285714285714,
-      "eval_loss": 1.209787130355835,
-      "eval_runtime": 20.5346,
-      "eval_samples_per_second": 4.87,
-      "eval_steps_per_second": 2.435,
-      "step": 6
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.3640616536140442,
-      "learning_rate": 0.00014,
-      "loss": 1.2188,
-      "step": 7
-    },
-    {
-      "epoch": 0.7619047619047619,
-      "grad_norm": 0.49822962284088135,
-      "learning_rate": 0.00016,
-      "loss": 1.2624,
-      "step": 8
-    },
-    {
-      "epoch": 0.8571428571428571,
-      "grad_norm": 0.42707493901252747,
-      "learning_rate": 0.00018,
-      "loss": 1.2697,
-      "step": 9
-    },
-    {
-      "epoch": 0.8571428571428571,
-      "eval_loss": 1.1909722089767456,
-      "eval_runtime": 20.1688,
-      "eval_samples_per_second": 4.958,
-      "eval_steps_per_second": 2.479,
-      "step": 9
-    },
-    {
-      "epoch": 0.9523809523809523,
-      "grad_norm": 0.27150899171829224,
-      "learning_rate": 0.0002,
-      "loss": 1.215,
-      "step": 10
-    },
-    {
-      "epoch": 1.0238095238095237,
-      "grad_norm": 0.23839783668518066,
-      "learning_rate": 0.00019876883405951377,
-      "loss": 1.2365,
-      "step": 11
-    },
-    {
-      "epoch": 1.119047619047619,
-      "grad_norm": 0.20644636452198029,
-      "learning_rate": 0.00019510565162951537,
-      "loss": 1.2243,
-      "step": 12
-    },
-    {
-      "epoch": 1.119047619047619,
-      "eval_loss": 1.1754947900772095,
-      "eval_runtime": 21.1588,
-      "eval_samples_per_second": 4.726,
-      "eval_steps_per_second": 2.363,
-      "step": 12
-    },
-    {
-      "epoch": 1.2142857142857142,
-      "grad_norm": 0.23169651627540588,
-      "learning_rate": 0.0001891006524188368,
-      "loss": 1.1474,
-      "step": 13
-    },
-    {
-      "epoch": 1.3095238095238095,
-      "grad_norm": 0.21209821105003357,
-      "learning_rate": 0.00018090169943749476,
-      "loss": 1.1395,
-      "step": 14
-    },
-    {
-      "epoch": 1.4047619047619047,
-      "grad_norm": 0.1954081654548645,
-      "learning_rate": 0.00017071067811865476,
-      "loss": 1.1981,
-      "step": 15
-    },
-    {
-      "epoch": 1.4047619047619047,
-      "eval_loss": 1.1603792905807495,
-      "eval_runtime": 16.71,
-      "eval_samples_per_second": 5.984,
-      "eval_steps_per_second": 2.992,
-      "step": 15
-    },
-    {
-      "epoch": 1.5,
-      "grad_norm": 0.17357416450977325,
-      "learning_rate": 0.00015877852522924732,
-      "loss": 1.1868,
-      "step": 16
-    },
-    {
-      "epoch": 1.5952380952380953,
-      "grad_norm": 0.16580979526042938,
-      "learning_rate": 0.00014539904997395468,
-      "loss": 1.1146,
-      "step": 17
-    },
-    {
-      "epoch": 1.6904761904761905,
-      "grad_norm": 0.20021770894527435,
-      "learning_rate": 0.00013090169943749476,
-      "loss": 1.1662,
-      "step": 18
-    },
-    {
-      "epoch": 1.6904761904761905,
-      "eval_loss": 1.149610996246338,
-      "eval_runtime": 6.2672,
-      "eval_samples_per_second": 15.956,
-      "eval_steps_per_second": 7.978,
-      "step": 18
-    },
-    {
-      "epoch": 1.7857142857142856,
-      "grad_norm": 0.20943716168403625,
-      "learning_rate": 0.0001156434465040231,
-      "loss": 1.228,
-      "step": 19
-    },
-    {
-      "epoch": 1.880952380952381,
-      "grad_norm": 0.215814009308815,
-      "learning_rate": 0.0001,
-      "loss": 1.2649,
-      "step": 20
-    },
-    {
-      "epoch": 1.9761904761904763,
-      "grad_norm": 0.17005658149719238,
-      "learning_rate": 8.435655349597689e-05,
-      "loss": 1.1879,
-      "step": 21
-    },
-    {
-      "epoch": 1.9761904761904763,
-      "eval_loss": 1.1423633098602295,
-      "eval_runtime": 6.4505,
-      "eval_samples_per_second": 15.503,
-      "eval_steps_per_second": 7.751,
-      "step": 21
-    },
-    {
-      "epoch": 2.0476190476190474,
-      "grad_norm": 0.20884154736995697,
-      "learning_rate": 6.909830056250527e-05,
-      "loss": 1.1346,
-      "step": 22
-    },
-    {
-      "epoch": 2.142857142857143,
-      "grad_norm": 0.1699027419090271,
-      "learning_rate": 5.4600950026045326e-05,
-      "loss": 1.1203,
-      "step": 23
-    },
-    {
-      "epoch": 2.238095238095238,
-      "grad_norm": 0.16104689240455627,
-      "learning_rate": 4.12214747707527e-05,
-      "loss": 1.198,
-      "step": 24
-    },
-    {
-      "epoch": 2.238095238095238,
-      "eval_loss": 1.141262173652649,
-      "eval_runtime": 6.2986,
-      "eval_samples_per_second": 15.876,
-      "eval_steps_per_second": 7.938,
-      "step": 24
-    },
-    {
-      "epoch": 2.3333333333333335,
-      "grad_norm": 0.16542628407478333,
-      "learning_rate": 2.9289321881345254e-05,
-      "loss": 1.1115,
-      "step": 25
-    },
-    {
-      "epoch": 2.4285714285714284,
-      "grad_norm": 0.16207309067249298,
-      "learning_rate": 1.9098300562505266e-05,
-      "loss": 1.19,
-      "step": 26
-    },
-    {
-      "epoch": 2.5238095238095237,
-      "grad_norm": 0.16097423434257507,
-      "learning_rate": 1.0899347581163221e-05,
-      "loss": 1.1981,
-      "step": 27
-    },
-    {
-      "epoch": 2.5238095238095237,
-      "eval_loss": 1.141075849533081,
-      "eval_runtime": 6.4063,
-      "eval_samples_per_second": 15.61,
-      "eval_steps_per_second": 7.805,
-      "step": 27
-    },
-    {
-      "epoch": 2.619047619047619,
-      "grad_norm": 0.16795802116394043,
-      "learning_rate": 4.8943483704846475e-06,
-      "loss": 1.1345,
-      "step": 28
-    },
-    {
-      "epoch": 2.7142857142857144,
-      "grad_norm": 0.16206511855125427,
-      "learning_rate": 1.231165940486234e-06,
-      "loss": 1.1223,
-      "step": 29
-    },
-    {
-      "epoch": 2.8095238095238093,
-      "grad_norm": 0.16133540868759155,
-      "learning_rate": 0.0,
-      "loss": 1.1377,
-      "step": 30
-    },
-    {
-      "epoch": 2.8095238095238093,
-      "eval_loss": 1.1379709243774414,
-      "eval_runtime": 6.1889,
-      "eval_samples_per_second": 16.158,
-      "eval_steps_per_second": 8.079,
-      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -319,12 +72,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5663067115094016.0,
+  "total_flos": 956760087330816.0,
   "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 sha256:7c62cd4a5f5b5d98624b05b91ea66842c68cee52403c2495c0459cf13d17cfcc
+oid sha256:992cb611dfba558f000caff8c8336327eaecf852390523fd335dc016a4bf9fd7
 size 6648