Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96247efa86b609e12dd162dc43c74d0f3a75eab0249d631432c3bd13972b4dd
+oid sha256:47e3cc8e04cedc525347989eedeef5e6871430b0c568bcc4f0f19c6a604d9ef0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac15eea5485c01d3befe07a14e9f7997d9dee335010a5c5b6c98dad423558e7
+oid sha256:ae5707fd45824773fec83395c846325bf944da931b472aac5c9d9e2af32528f1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 0.0001690974424011837,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002198266751215388,
+  "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": 0.0001690974424011837,
       "eval_loss": 4.695179462432861,
-      "eval_runtime": 144.154,
-      "eval_samples_per_second": 17.273,
-      "eval_steps_per_second": 8.637,
+      "eval_runtime": 144.0478,
+      "eval_samples_per_second": 17.286,
+      "eval_steps_per_second": 8.643,
       "step": 1
+    },
+    {
+      "epoch": 0.0008454872120059184,
+      "grad_norm": 7.579517841339111,
+      "learning_rate": 5e-05,
+      "loss": 4.7342,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016909744240118367,
+      "grad_norm": 7.856087684631348,
+      "learning_rate": 0.0001,
+      "loss": 3.2303,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016909744240118367,
+      "eval_loss": 1.0427312850952148,
+      "eval_runtime": 144.9035,
+      "eval_samples_per_second": 17.184,
+      "eval_steps_per_second": 8.592,
+      "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": 162873313591296.0,
+  "total_flos": 2117353076686848.0,
   "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:d9264a0960600b80440f5568bb9be15fb05656f3dc6c2fae766f4e82160951c3
+oid sha256:ee5ea1f38e6046ae5f7f9b6201be9dce67d63b0e110c2b903c6379e9e5c59663
 size 6776