Training in progress, step 4, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "q_proj",
     "k_proj",
-    "down_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj",
-    "q_proj",
-    "o_proj",
-    "gate_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:bcbf06858a2c60c6f7d335522a0fc9e4928ea47704df9578855c158e4b52206a
+oid sha256:5d0165165d309efe2bc67ec47e2fb6939609fabc938111d98e7b1570542826dd
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760c4e18ab7ab170887c10a99b231caf9e23fef29d0d811a737ed5b6d478d603
+oid sha256:cebde071ebc7692d3308fd8930794e495278090d35bb7ce7c201261abdb2c13b
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ac0c668385ad2b9aa96b4a6520400841eeb43e87268e46a61e0b348e499755
+oid sha256:f50cc0a3e92dca42053d2ef622567a9f710a3429c2adfbbce542167578fceae6
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ecbb76344ff458defacd3ba4d074ae53be644437725a0992f0f61f74c5530f
+oid sha256:0140d392838184af026303533cb58f2174562eda6a4742ff6da5b3d95df2f9ec
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,85 +1,71 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
-  "eval_steps": 3,
-  "global_step": 6,
+  "epoch": 0.6666666666666666,
+  "eval_steps": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.08333333333333333,
+      "epoch": 0.16666666666666666,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.4924,
+      "loss": 1.3997,
       "step": 1
     },
     {
-      "epoch": 0.08333333333333333,
-      "eval_loss": 1.4975985288619995,
-      "eval_runtime": 0.1911,
-      "eval_samples_per_second": 15.701,
-      "eval_steps_per_second": 15.701,
+      "epoch": 0.16666666666666666,
+      "eval_loss": 1.4973297119140625,
+      "eval_runtime": 0.2886,
+      "eval_samples_per_second": 10.395,
+      "eval_steps_per_second": 6.93,
       "step": 1
     },
     {
-      "epoch": 0.16666666666666666,
-      "grad_norm": 5.183752536773682,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 5.478867530822754,
       "learning_rate": 2e-05,
-      "loss": 1.3074,
+      "loss": 1.4535,
       "step": 2
     },
     {
-      "epoch": 0.25,
-      "grad_norm": 6.239664077758789,
-      "learning_rate": 4e-05,
-      "loss": 1.5739,
-      "step": 3
+      "epoch": 0.3333333333333333,
+      "eval_loss": 1.4973297119140625,
+      "eval_runtime": 0.284,
+      "eval_samples_per_second": 10.565,
+      "eval_steps_per_second": 7.043,
+      "step": 2
     },
     {
-      "epoch": 0.25,
-      "eval_loss": 1.4466005563735962,
-      "eval_runtime": 0.211,
-      "eval_samples_per_second": 14.216,
-      "eval_steps_per_second": 14.216,
+      "epoch": 0.5,
+      "grad_norm": 5.20695686340332,
+      "learning_rate": 4e-05,
+      "loss": 1.5303,
       "step": 3
     },
     {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 5.012392044067383,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 4.481665134429932,
       "learning_rate": 6e-05,
-      "loss": 1.2793,
+      "loss": 1.394,
       "step": 4
     },
     {
-      "epoch": 0.4166666666666667,
-      "grad_norm": 3.691774845123291,
-      "learning_rate": 8e-05,
-      "loss": 1.3057,
-      "step": 5
-    },
-    {
-      "epoch": 0.5,
-      "grad_norm": 3.0195882320404053,
-      "learning_rate": 0.0001,
-      "loss": 1.0885,
-      "step": 6
-    },
-    {
-      "epoch": 0.5,
-      "eval_loss": 0.8231927752494812,
-      "eval_runtime": 0.2024,
-      "eval_samples_per_second": 14.826,
-      "eval_steps_per_second": 14.826,
-      "step": 6
+      "epoch": 0.6666666666666666,
+      "eval_loss": 1.2689329385757446,
+      "eval_runtime": 0.3021,
+      "eval_samples_per_second": 9.93,
+      "eval_steps_per_second": 6.62,
+      "step": 4
     }
   ],
   "logging_steps": 1,
-  "max_steps": 10,
+  "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 3,
+  "save_steps": 2,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -92,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1479651398516736.0,
   "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:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
+oid sha256:74dcf4a29346d06a18985986c93532599870827345febcfc1739afefe0e2e2b9
 size 6776