Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
+    "up_proj",
     "down_proj",
+    "gate_proj",
+    "v_proj",
     "k_proj",
-    "o_proj",
-    "up_proj",
-    "gate_proj"
+    "q_proj",
+    "o_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 sha256:423b8a33a6956ce9e257c82bd8928c23fe279be18d309135f115c755c27ae61d
+oid sha256:ed9144ceb1379abeeddfd0fe774d552981a5e19994d93bb06f2cd152d39e50d7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997fdc08a5843bcfee03230ff3d85b6bf316554a7aae7296c6a1b2e4e00e8621
+oid sha256:9aac4a36e033970ba990f0eaaed177fdecfdcd32f20655f5c1c59b791e408183
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:3dfaa76e23b5ee2e9cd9f372437b6e2eeffe609e58ae8d131d3303166f82dc47
 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": 0.0025412960609911056,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03303684879288437,
+  "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": 0.0025412960609911056,
       "eval_loss": 3.9905848503112793,
-      "eval_runtime": 11.4536,
-      "eval_samples_per_second": 14.493,
-      "eval_steps_per_second": 7.247,
+      "eval_runtime": 11.5089,
+      "eval_samples_per_second": 14.424,
+      "eval_steps_per_second": 7.212,
       "step": 1
+    },
+    {
+      "epoch": 0.012706480304955527,
+      "grad_norm": 5.360012054443359,
+      "learning_rate": 5e-05,
+      "loss": 3.8354,
+      "step": 5
+    },
+    {
+      "epoch": 0.025412960609911054,
+      "grad_norm": 6.536111354827881,
+      "learning_rate": 0.0001,
+      "loss": 3.5027,
+      "step": 10
+    },
+    {
+      "epoch": 0.025412960609911054,
+      "eval_loss": 2.754293441772461,
+      "eval_runtime": 11.7031,
+      "eval_samples_per_second": 14.184,
+      "eval_steps_per_second": 7.092,
+      "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": 184959646040064.0,
+  "total_flos": 2589435044560896.0,
   "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 sha256:3291ab2fefecbc2189d3c5a6073d34ef4e24b31d7f2f3662fa2c19de481840e2
+oid sha256:ea052a740d80abda7f10e75c125a5d4f3ee2f32c17e26fd205ae67a40ed5cbcb
 size 6776