Training in progress, step 1348, checkpoint

last-checkpoint/README.md

@@ -1,6 +1,6 @@
 ---
-base_model: Qwen/Qwen2-1.5B
 library_name: peft
+base_model: Qwen/Qwen2-1.5B
 ---
 
 # Model Card for Model ID

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
-    "v_proj",
     "q_proj",
-    "o_proj",
-    "up_proj",
+    "v_proj",
     "gate_proj",
-    "k_proj"
+    "k_proj",
+    "up_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 sha256:688843da1640c32ce4e5b0dd415b4745d092e74adc129c5ca5976d05f958b1c0
+oid sha256:b3558d431079f44877a9d7ec7689bf9dec9d0acaa969eea150b64bb60fb9feba
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e26ac250efb68381f21d0b5da0c97cffc6cd2447f34c899d92f813190adf8781
+oid sha256:f5e2321aff39041aff312af042dcb569c4492f688d2850360704dfce441cc3c4
 size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac47ffdc8bf5525523430933f676efab1c80d316d9cff3d1dfe55769817ffdf
+oid sha256:a23f0ae2b830e333bafe3304c20b79c00db6d8ee17a5eb324f391614c72f5740
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72baa363e8d8009e6670ef03c726c7c624204de1feda6a1a3552ee81c1f0fa95
+oid sha256:9f1ab2b4a19233475e302a6e57417dafa209767a2407b98a152443e29f7a4225
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5207654433477779,
+  "epoch": 0.5223153405005986,
   "eval_steps": 500,
-  "global_step": 1344,
+  "global_step": 1348,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9415,6 +9415,34 @@
       "learning_rate": 4.8260545004765034e-06,
       "loss": 1.4037,
       "step": 1344
+    },
+    {
+      "epoch": 0.521152917635983,
+      "grad_norm": 0.16563992202281952,
+      "learning_rate": 4.819844804562982e-06,
+      "loss": 1.369,
+      "step": 1345
+    },
+    {
+      "epoch": 0.5215403919241882,
+      "grad_norm": 0.1691073179244995,
+      "learning_rate": 4.8136353868720215e-06,
+      "loss": 1.3619,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5219278662123934,
+      "grad_norm": 0.1665688157081604,
+      "learning_rate": 4.807426256993129e-06,
+      "loss": 1.4184,
+      "step": 1347
+    },
+    {
+      "epoch": 0.5223153405005986,
+      "grad_norm": 0.19875416159629822,
+      "learning_rate": 4.801217424515373e-06,
+      "loss": 1.3861,
+      "step": 1348
     }
   ],
   "logging_steps": 1.0,
@@ -9434,7 +9462,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3305286607076035e+18,
+  "total_flos": 1.3343332572853494e+18,
   "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 sha256:215e03d579d5bead586fbfbe9f265c136f4ce5e15ab6e9bf675e8b1e4eedaeb9
+oid sha256:ccab74b7d59afe7cc3e4a4fcf258823ef918544b3b8f3bc7776c7753e86981da
 size 5560