Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
     "up_proj",
     "o_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj",
-    "down_proj"
+    "v_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 sha256:248eb77cd6f6bbad7d1bcc7110ff200ac54b7115a21c51c156d8e51f8563ebc1
+oid sha256:1ddd0bfa337995872206a908ff6c31d7f22a65a8b352afcb3f79bb895124bf8f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50034867d33500fcbca5f263e64df4948cb0350e33b3094632dfba4eacd405fe
-size 2216
+oid sha256:45f8c3c9aa5490a356e1a0bf3d542da3411c36bd7c0824d4df71dd45b464b55e
+size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8441b6f44f4e2fa1d2c030527340ac0218aae059aebad5b78181cb84cf26fe
+oid sha256:d79213b91105086d030b1e0778fbe7d6283f4c083ba909b2ec62c9e7ab91b108
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc75c68691d11d10bcc57bd372463d3e0df9a0caca3bec2a2287a78f782bdcb7
+oid sha256:b610e79daca538339e134160174e96c554fad20f4a4463e6c489c0e388d47d5e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,49 +1,107 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008982708286548395,
+  "epoch": 0.005389221556886228,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0002994236095516131,
+      "epoch": 0.0005988023952095808,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 10.9802,
+      "loss": 10.8959,
       "step": 1
     },
     {
-      "epoch": 0.0002994236095516131,
-      "eval_loss": 11.5775728225708,
-      "eval_runtime": 95.8227,
-      "eval_samples_per_second": 7.347,
-      "eval_steps_per_second": 7.347,
+      "epoch": 0.0005988023952095808,
+      "eval_loss": 11.577476501464844,
+      "eval_runtime": 47.7616,
+      "eval_samples_per_second": 14.74,
+      "eval_steps_per_second": 7.37,
       "step": 1
     },
     {
-      "epoch": 0.0005988472191032262,
+      "epoch": 0.0011976047904191617,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 10.7165,
+      "loss": 10.0136,
       "step": 2
     },
     {
-      "epoch": 0.0008982708286548395,
+      "epoch": 0.0017964071856287425,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 10.434,
+      "loss": 11.649,
       "step": 3
     },
     {
-      "epoch": 0.0008982708286548395,
-      "eval_loss": 11.5775728225708,
-      "eval_runtime": 95.0865,
-      "eval_samples_per_second": 7.404,
-      "eval_steps_per_second": 7.404,
+      "epoch": 0.0017964071856287425,
+      "eval_loss": 11.577476501464844,
+      "eval_runtime": 47.9565,
+      "eval_samples_per_second": 14.68,
+      "eval_steps_per_second": 7.34,
       "step": 3
+    },
+    {
+      "epoch": 0.0023952095808383233,
+      "grad_norm": 9.167847633361816,
+      "learning_rate": 2e-05,
+      "loss": 11.4872,
+      "step": 4
+    },
+    {
+      "epoch": 0.0029940119760479044,
+      "grad_norm": 6.535604953765869,
+      "learning_rate": 4e-05,
+      "loss": 9.9558,
+      "step": 5
+    },
+    {
+      "epoch": 0.003592814371257485,
+      "grad_norm": 8.272323608398438,
+      "learning_rate": 6e-05,
+      "loss": 11.9577,
+      "step": 6
+    },
+    {
+      "epoch": 0.003592814371257485,
+      "eval_loss": 11.506834983825684,
+      "eval_runtime": 47.6191,
+      "eval_samples_per_second": 14.784,
+      "eval_steps_per_second": 7.392,
+      "step": 6
+    },
+    {
+      "epoch": 0.004191616766467066,
+      "grad_norm": 8.094924926757812,
+      "learning_rate": 8e-05,
+      "loss": 12.3056,
+      "step": 7
+    },
+    {
+      "epoch": 0.004790419161676647,
+      "grad_norm": 9.111627578735352,
+      "learning_rate": 0.0001,
+      "loss": 9.0397,
+      "step": 8
+    },
+    {
+      "epoch": 0.005389221556886228,
+      "grad_norm": 6.980569839477539,
+      "learning_rate": 0.00012,
+      "loss": 9.2177,
+      "step": 9
+    },
+    {
+      "epoch": 0.005389221556886228,
+      "eval_loss": 10.915068626403809,
+      "eval_runtime": 47.9969,
+      "eval_samples_per_second": 14.668,
+      "eval_steps_per_second": 7.334,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 3329215646662656.0,
   "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 sha256:1ee223a43027b8c8afd21622e4578463f433159b96d4ac348cc6f399af5db597
+oid sha256:6bc64a63498e1a4fd3792d98994b6d4b37c859bdb415f82833cc56bc99d4df9e
 size 6776