Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "up_proj",
-    "q_proj",
-    "down_proj",
     "o_proj",
     "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aaf8240dd8296d7090d5d91a890b0024903218539fee1cdd841a22261a9f29d
+oid sha256:8ffe12a6d840a6bf89e7ca24241d225759756716cf217bbbc6633d7209e0bb0f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377c261e25ead17181ddb278b37dfc770d3931c8b2e3de9012e906bfd7ceee53
+oid sha256:80ffcdebfe586d10c951ed5afb46f5c2885856f6b424580d0eadf7ef408ae3a8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.139483635624542e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00027813287263119045,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 2.139483635624542e-05,
       "eval_loss": 3.5064687728881836,
-      "eval_runtime": 1313.2941,
-      "eval_samples_per_second": 14.986,
-      "eval_steps_per_second": 7.493,
+      "eval_runtime": 1313.719,
+      "eval_samples_per_second": 14.981,
+      "eval_steps_per_second": 7.491,
       "step": 1
+    },
+    {
+      "epoch": 0.0001069741817812271,
+      "grad_norm": 3.9627699851989746,
+      "learning_rate": 5e-05,
+      "loss": 3.4034,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002139483635624542,
+      "grad_norm": 4.111531734466553,
+      "learning_rate": 0.0001,
+      "loss": 2.8548,
+      "step": 10
+    },
+    {
+      "epoch": 0.0002139483635624542,
+      "eval_loss": 1.7997324466705322,
+      "eval_runtime": 1311.2175,
+      "eval_samples_per_second": 15.01,
+      "eval_steps_per_second": 7.505,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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:c46fb5919a58d9e60653892e58635553b445f7837148b35a13c7111bc13cb1b2
+oid sha256:2b17f7d446e8454bc9ba54ac293851bebe1a37ac22181b7642ee560e7661dc5c
 size 6776