Training in progress, step 10, checkpoint

checkpoint-10/adapter_config.json

@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "q_proj",
     "v_proj",
-    "o_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee918aa4168b0cd5bfc7b77611564c742ece171be52e6497ff5fb1de8ea0a53
+oid sha256:1e888ba5b357cca479fdfb83c7a6d1d517139cd69f31a8e5d2b0f19b95f96156
 size 27297032

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0047d262f324b7d9b48aad39e6425642f9024540da81b6b9924a1adb0faf216b
+oid sha256:38e7804f61425e5bc724e211e81e2632de062c48494ab6889553a89535b9b858
 size 54678010

checkpoint-10/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f446d1d665fe499a7e8afff583956eaaf2eb2926c47d7d56c7673b47ebeae0f
+oid sha256:71deba4f5cbb7f14856592e6b45f65cdbc27ef90ce55c1b4360b28f0d3af92eb
 size 14512

checkpoint-10/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0f49f313692f7751e85aa52cfaddccbd9736d47a2f079a4b68f4856eba8ac4
+oid sha256:fd1064c84cc8895e25cf176f0a6304640003de5efcfb37abf2faf7263c4c86b7
 size 14512

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.2618540525436401,
+  "best_metric": 1.2620933055877686,
   "best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
   "epoch": 0.006199628022318661,
   "eval_steps": 10,
@@ -10,10 +10,10 @@
   "log_history": [
     {
       "epoch": 0.01,
-      "eval_loss": 1.2618540525436401,
-      "eval_runtime": 210.4635,
-      "eval_samples_per_second": 13.622,
-      "eval_steps_per_second": 3.407,
+      "eval_loss": 1.2620933055877686,
+      "eval_runtime": 214.1744,
+      "eval_samples_per_second": 13.386,
+      "eval_steps_per_second": 3.348,
       "step": 10
     }
   ],
@@ -22,7 +22,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 5127998751637504.0,
+  "total_flos": 5344598247342080.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b299bd5cc2268988933042a1007b13e809128e91e8b83f90595fa635ae59af06
+oid sha256:4a7b951862cc1b6fc3818abc40db6d785393d7d2119a2d8adb59ac9fe86d702f
 size 5112