Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "o_proj",
     "up_proj",
     "gate_proj",
-    "down_proj",
+    "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj",
-    "k_proj"
+    "down_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 sha256:0eea3eb71370999fc170b6fa4b35eaa72f5adea8bee62ee75c62ab28c440990b
+oid sha256:c7e1faaa35cb6b33b63967bf8ef495a5819cb9947f60831e92b48039e6b01d61
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f15493f2c88a99dd6bfa8af3942b6c89bb155d6a2f956a6c190ae681a62976
+oid sha256:c3275eae0f893f76fb9da2e38a6641d428a5e80f1afc211afedb92516c3308ee
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fae2f082bc2b8a4f93f074fb88d1c6113a4081d21b0babdad2ac6534f83080
+oid sha256:b655aa04cd69eb88911f7013728dde1b484b8ddf3bd446150aae9d5558c1b4fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:aea67b5da66f242c315a67190bee42ac01d2c7b5f9d79262964d41c22411bb70
 size 1064

last-checkpoint/trainer_state.json

@@ -1,120 +1,61 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025789813023855575,
-  "eval_steps": 3,
-  "global_step": 10,
+  "epoch": 0.02577319587628866,
+  "eval_steps": 97,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0025789813023855577,
-      "grad_norm": 1.0605525970458984,
-      "learning_rate": 2e-05,
-      "loss": 1.0005,
+      "epoch": 0.005154639175257732,
+      "grad_norm": 0.8343322277069092,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.9672,
       "step": 1
     },
     {
-      "epoch": 0.0025789813023855577,
-      "eval_loss": 1.0008567571640015,
-      "eval_runtime": 25.1865,
-      "eval_samples_per_second": 6.511,
-      "eval_steps_per_second": 3.256,
+      "epoch": 0.005154639175257732,
+      "eval_loss": 0.986353874206543,
+      "eval_runtime": 22.8548,
+      "eval_samples_per_second": 7.176,
+      "eval_steps_per_second": 1.794,
       "step": 1
     },
     {
-      "epoch": 0.0051579626047711154,
-      "grad_norm": 1.0020190477371216,
-      "learning_rate": 4e-05,
-      "loss": 0.9353,
+      "epoch": 0.010309278350515464,
+      "grad_norm": 0.7854290008544922,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0214,
       "step": 2
     },
     {
-      "epoch": 0.007736943907156673,
-      "grad_norm": 1.1047412157058716,
-      "learning_rate": 6e-05,
-      "loss": 0.9902,
+      "epoch": 0.015463917525773196,
+      "grad_norm": 0.7100067734718323,
+      "learning_rate": 6e-06,
+      "loss": 0.8938,
       "step": 3
     },
     {
-      "epoch": 0.007736943907156673,
-      "eval_loss": 0.9955174326896667,
-      "eval_runtime": 25.348,
-      "eval_samples_per_second": 6.47,
-      "eval_steps_per_second": 3.235,
-      "step": 3
-    },
-    {
-      "epoch": 0.010315925209542231,
-      "grad_norm": 0.9929641485214233,
-      "learning_rate": 8e-05,
-      "loss": 1.1196,
+      "epoch": 0.020618556701030927,
+      "grad_norm": 0.80195152759552,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.901,
       "step": 4
     },
     {
-      "epoch": 0.012894906511927788,
-      "grad_norm": 0.6895298957824707,
-      "learning_rate": 0.0001,
-      "loss": 0.8578,
+      "epoch": 0.02577319587628866,
+      "grad_norm": 1.1374644041061401,
+      "learning_rate": 1e-05,
+      "loss": 1.0694,
       "step": 5
-    },
-    {
-      "epoch": 0.015473887814313346,
-      "grad_norm": 0.8787553906440735,
-      "learning_rate": 0.00012,
-      "loss": 0.8842,
-      "step": 6
-    },
-    {
-      "epoch": 0.015473887814313346,
-      "eval_loss": 0.9533936977386475,
-      "eval_runtime": 25.2724,
-      "eval_samples_per_second": 6.489,
-      "eval_steps_per_second": 3.245,
-      "step": 6
-    },
-    {
-      "epoch": 0.018052869116698903,
-      "grad_norm": 0.8236719369888306,
-      "learning_rate": 0.00014,
-      "loss": 0.927,
-      "step": 7
-    },
-    {
-      "epoch": 0.020631850419084462,
-      "grad_norm": 0.7619084119796753,
-      "learning_rate": 0.00016,
-      "loss": 0.8342,
-      "step": 8
-    },
-    {
-      "epoch": 0.02321083172147002,
-      "grad_norm": 0.6021698713302612,
-      "learning_rate": 0.00018,
-      "loss": 0.9599,
-      "step": 9
-    },
-    {
-      "epoch": 0.02321083172147002,
-      "eval_loss": 0.9017542600631714,
-      "eval_runtime": 25.2951,
-      "eval_samples_per_second": 6.483,
-      "eval_steps_per_second": 3.242,
-      "step": 9
-    },
-    {
-      "epoch": 0.025789813023855575,
-      "grad_norm": 0.6562431454658508,
-      "learning_rate": 0.0002,
-      "loss": 0.8921,
-      "step": 10
     }
   ],
   "logging_steps": 1,
-  "max_steps": 10,
+  "max_steps": 970,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 5,
   "save_steps": 5,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -123,13 +64,13 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
   "total_flos": 1935445139128320.0,
-  "train_batch_size": 2,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f3c45f7c59d900a8d713fe61102ed0176a9426e9358581ab3c6c36dc9ee7c0f
+oid sha256:41ac17a433d423013a7c5c139f39fb73f110d9661b1388568e3110e7de55ea03
 size 6648